Interpreting Evo 2: Arc Institute's Next-Generation Genomic Foundation Model

Introducing “Interpretable” Evo 2

Why This Matters

Biological foundation models represent a unique challenge and opportunity for AI interpretability. Unlike language models that process human-readable text, these neural networks operate on DNA sequences—a biological code that even human experts struggle to directly read and understand. Evo 2 works with an especially complex version of this challenge, processing multiple layers of biological information: from raw DNA sequences to the proteins they encode, and the intricate RNA structures they form. By applying state-of-the-art interpretability techniques (similar to those detailed in our Understanding and Steering Llama 3 paper), we hope to:

• Extract and analyze previously hidden biological knowledge within these models, potentially revealing novel mechanisms and patterns
• Enable biologists to conduct targeted experiments at unprecedented scale through controlled DNA sequence generation

This interpretability breakthrough could deepen our understanding of biological systems while enabling new approaches to genome engineering. These advances open possibilities for developing better disease treatments and improving human health.

We provide a high level overview of the work we’ve done below. The mechanistic interpretability sections (2.4, 4.4) of the preprint contain more detailed information on our findings.

Interpreter model overview

Training an Evo 2 interpreter model (sparse autoencoder or SAE)

We have some early signs of life on steering Evo 2 to precisely engineer new protein structures, but steering this model is considerably more complex than steering a language model. Further research is needed to unlock the full potential of this approach. The potential impact of steering Evo 2 is particularly significant: while language models can be prompted to achieve desired behaviors, a model that ‘only speaks nucleotide’ cannot. Learning to steer through features would unlock entirely new capabilities.

Why did we switch to BatchTopK?

We chose an even mix of eukaryotic and prokaryotic data in order to find both domain-specific and generalizing features. Because SAEs obtain interesting and useful features with relatively little data compared to foundation models, we were able to make use of only high-quality reference genomes from both domains.

Why layer 26?

We trained SAEs on multiple layers of the model, including both Transformer and StripedHyena layers. Layer 26 (a StripedHyena layer) had the most interesting biologically-relevant features on an initial inspection, so we focused additional effort on studying this layer.

Evo 2 7B has 32 layers, so layer 26 is relatively late compared to our natural language model SAEs. This might be due to the much lower vocabulary size: a nucleotide-level model of the genome has very few tokens in its vocabulary (primarily A, T, C, G, though some additional tokens are also used during training) compared to the very large vocabulary size of a natural language model. This might mean that once the relevant patterns have been computed, fewer layers of the model are then required to both select the relevant next token and correctly calibrate probabilities between plausible options.

Deciphering Evo 2’s latent space

Visualizing interpretable features from our Evo 2 SAE

To make these features more tangible, we built an interactive feature visualizer showcasing some example SAE features as they relate to known biological concepts. Here, you can see activation values of these features across a set of bacterial reference genomes and how they align with existing genomic annotations.

For example, we discovered that the model has learned to identify several key biological concepts, including:

• Coding sequences (the parts of DNA that contain instructions for building proteins)

• Protein secondary structure (common shapes that proteins fold into such as α-helices and β-sheets)

• tRNA/rRNAs (RNA molecules involved in protein synthesis)

• Viral derived sequences (prophage and CRISPR elements)

Annotating a bacterial genome

Additional noteworthy examples

You can reference Figure 4 in the preprint to learn more about the most salient features we discovered across the various scales of biological complexity.

Looking Ahead

This announcement provides a high-level overview of our work with Arc Institute. We’re currently working to publish a more comprehensive study in the coming months that will detail our interpretability methodology.

We’re excited about AI interpretability’s potential to accelerate meaningful scientific discovery. If you’re working on scientific foundation models, we’d love to explore how we can help interpret them.

Relevant Links

• Evo 2 Announcement
• Evo 2 Preprint
• Evo 2 Mechanistic Interpretability Feature Visualizer