© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 7510
    Prev
    Next
    INDEX
    Explanations

    instances of the word "com" and references to file handling functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sẻ
    -0.56
     indisponible
    -0.54
     hacia
    -0.50
     fraî
    -0.50
    <bos>
    -0.50
    ViewImports
    -0.48
    */),
    -0.47
    好不好
    -0.47
     oignons
    -0.47
     thuyền
    -0.47
    POSITIVE LOGITS
    Bronnen
    0.90
    addContainerGap
    0.76
     الاطلاع
    0.68
    CloseOperation
    0.66
    secta
    0.61
    localctx
    0.61
     Orrell
    0.61
    eningen
    0.60
    Ï
    0.59
     للاسماء
    0.59
    Activations Density 0.012%

    No Known Activations