© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 644
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schulte
    -0.83
    `;
    -0.71
     Münch
    -0.69
    égard
    -0.69
    ంది
    -0.68
    /
    -0.67
    тони
    -0.67
    }]
    -0.66
     Wikimédia
    -0.66
    /');
    -0.66
    POSITIVE LOGITS
     How
    2.40
    How
    2.34
     how
    2.16
    how
    1.98
     HOW
    1.95
    HOW
    1.88
     कैसे
    1.43
     cómo
    1.33
    howto
    1.30
     如何
    1.29
    Activations Density 0.058%

    No Known Activations