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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 22366
    Prev
    Next
    INDEX
    Explanations

    span tags in HTML or other markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    }{*}{}
    -0.65
     MainAxisSize
    -0.57
    IsSuccess
    -0.49
     Wikimedijinoj
    -0.49
    $_.
    -0.47
    RegressionTest
    -0.45
    دانشنامهٔ
    -0.45
    Panamoan
    -0.44
    endregion
    -0.44
     Roskov
    -0.44
    POSITIVE LOGITS
    <i>
    0.66
     <<<<<<<<<<<<<<
    0.66
     تضيفلها
    0.59
    <em>
    0.58
    <strong>
    0.54
    <u>
    0.53
    <b>
    0.52
    󠁧
    0.52
    <0xCA>
    0.50
     păr
    0.49
    Activations Density 0.015%

    No Known Activations