© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10188
    Prev
    Next
    INDEX
    Explanations

    key programming constructs and file handling operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    string and file path variables in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    variable names and file paths in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    programming identifiers and resource names in code (variable/class names, filenames, constants), rather than language keywords or syntax.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.81
    awtextra
    -0.79
    ImageContext
    -0.78
    +#+#
    -0.77
     ErrIntOverflow
    -0.74
     disponibilités
    -0.73
     BoxFit
    -0.70
    setViewportView
    -0.69
     ModelExpression
    -0.69
    Vidite
    -0.68
    POSITIVE LOGITS
    ,
    0.42
     using
    0.33
     sambil
    0.31
     without
    0.29
     under
    0.29
     وذلك
    0.28
     ślub
    0.28
    $,
    0.27
     hoping
    0.27
     dépasse
    0.26
    Activations Density 0.434%

    No Known Activations