Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior

Google DeepMind Blog11 months ago

11mo

Age

Published: Dec 16, 2025, 10:14 AM UTC
Collected: Aug 19, 2026, 8:28 AM UTC

Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.

Read the full article at deepmind.google

overfeed.news indexes and links. We publish a short excerpt — the full article stays at Google DeepMind Blog.

More from Google DeepMind Blog

Log in to follow this source

Google DeepMind Blog4 hours ago

Introducing Gemini 4 Hydrogen

Google DeepMind Blogyesterday

AlphaGenome 2: Deciphering how cells read DNA to better understand disease

Predicting how DNA sequences and their variations impact specific human cell types and disease.

Google DeepMind Blog2 days ago

Gemini 4 Carbon is now available

Google DeepMind Blog2 days ago

Introducing AlphaProof Code: a breakthrough in verifying complex software at depth

AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.

Gemma Scope 2: helping the AI safety community deepen…