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. 20-GEMMASCOPE-RES-131K
    6. 70694
    Prev
    Next
    INDEX
    Explanations

    content related to governance, procedural matters, and legal frameworks

    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
    1
    -0.33
    the
    -0.32
     Austin
    -0.30
    else
    -0.30
    jącej
    -0.29
    (
    -0.29
    rv
    -0.28
    <
    -0.28
    AUTH
    -0.28
    Ignored
    -0.27
    POSITIVE LOGITS
     &___
    0.77
    aarrggbb
    0.73
     nonUne
    0.73
     للاسماء
    0.72
    majánló
    0.69
     الرياضيه
    0.68
    存于互联网档案馆
    0.68
    Diweddarwch
    0.67
    @[+][
    0.66
    localctx
    0.66
    Activations Density 0.216%

    No Known Activations