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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1046
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "export" in code or documentation

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

    export statements in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.62
    writeFieldEnd
    -0.62
    onedDateTime
    -0.59
     betweenstory
    -0.56
    CodedInputStream
    -0.56
    rrggbb
    -0.52
    principalColumn
    -0.52
     Biôgrafia
    -0.52
    +#+
    -0.52
     يتيمه
    -0.51
    POSITIVE LOGITS
    export
    0.91
     export
    0.60
    public
    0.59
    EXPORT
    0.58
     Export
    0.57
    Export
    0.57
    exports
    0.51
    IBOutlet
    0.49
    पया
    0.45
    ăsp
    0.43
    Activations Density 0.001%

    No Known Activations