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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 16027
    Prev
    Next
    INDEX
    Explanations

    specific formatting patterns and punctuation in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !
    -0.43
    -
    -0.42
     these
    -0.39
     in
    -0.35
     biryani
    -0.34
    —
    -0.34
     contrase
    -0.34
     for
    -0.33
    ...
    -0.33
    críbete
    -0.32
    POSITIVE LOGITS
     Various
    0.91
     The
    0.85
     Himself
    0.77
     Unknown
    0.73
     Chriftian
    0.71
    Various
    0.69
     None
    0.69
    Unnamed
    0.67
    +};
    0.67
     Jefus
    0.66
    Activations Density 0.654%

    No Known Activations