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-2-2B
    4. Residual Stream - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1807
    Prev
    Next
    INDEX
    Explanations

    structured data and formats within technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tispiece
    -0.53
    جغرافيا
    -0.52
    InsertCommand
    -0.52
    xodo
    -0.51
     Emits
    -0.49
    bunifu
    -0.49
    Kapcsolódó
    -0.48
    WebpackPlugin
    -0.48
    xticks
    -0.47
    Linki
    -0.46
    POSITIVE LOGITS
    __*/
    0.62
     समीक्षाओं
    0.62
    󠁴
    0.61
    HomeAsUpEnabled
    0.61
     betweenstory
    0.59
     <=",
    0.57
    Lähteet
    0.56
    GEBURTSDATUM
    0.56
    ⤹
    0.55
    눠
    0.53
    Activations Density 1.058%

    No Known Activations