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. 114937
    Prev
    Next
    INDEX
    Explanations

    special characters or unusual formatting in text

    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
     sond
    -0.41
    ↵
    -0.41
     ά
    -0.41
    ❉
    -0.40
    <table>
    -0.40
    ↵↵
    -0.38
    WORTH
    -0.38
    向
    -0.38
     pr
    -0.38
    盛
    -0.38
    POSITIVE LOGITS
    SharedCtor
    0.65
    bibfield
    0.56
    BibitemShut
    0.56
     OMITBAD
    0.54
    citenamefont
    0.54
     Bewußt
    0.53
    ToBounds
    0.52
    ́
    0.52
    出版年
    0.51
    NewUrlParser
    0.51
    Activations Density 0.012%

    No Known Activations