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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6576
    Prev
    Next
    INDEX
    Explanations

    code blocks or statements that indicate the end of a function or block of code

    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
    pexpr
    -0.74
     SwitchCompat
    -0.72
    Chham
    -0.69
     Zacks
    -0.68
     Himo
    -0.64
    GEBURTS
    -0.63
    ♭
    -0.63
    WebServlet
    -0.63
    InputTagHelper
    -0.62
     itſelf
    -0.61
    POSITIVE LOGITS
    endphp
    1.10
    endsection
    0.90
    glEnd
    0.86
    </table>
    0.85
    }());
    0.84
    })();
    0.82
    endforeach
    0.80
    endpush
    0.80
    end
    0.80
     {}));
    0.77
    Activations Density 0.053%

    No Known Activations