Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 130004
    Prev
    Next
    INDEX
    Explanations

    programming function declarations and export statements in code

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

    function, exports, or related topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.39
    creativecommons
    -0.33
    SuppressMessage
    -0.33
    ContentAlignment
    -0.32
     resultSet
    -0.31
    lots
    -0.30
    DotNet
    -0.30
     CascadeType
    -0.28
     nonché
    -0.28
    slidesToShow
    -0.27
    POSITIVE LOGITS
     EconPapers
    0.68
    SharedDtor
    0.67
    rungsseite
    0.59
    Personensuche
    0.59
    úgó
    0.57
    @[+][
    0.56
    FunctionFlags
    0.56
     exports
    0.54
    exports
    0.53
     Exports
    0.52
    Activations Density 0.005%

    No Known Activations