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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14776
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with mythology and historical figures

    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
    脚注の使い方
    -0.82
    yarnpkg
    -0.76
    addPreferredGap
    -0.74
     opérateur
    -0.70
    waltung
    -0.70
    ῳ
    -0.70
    jangkau
    -0.69
    CloseOperation
    -0.69
    tableFuture
    -0.67
    byshev
    -0.67
    POSITIVE LOGITS
     TUS
    1.01
     PPS
    0.99
    nes
    0.93
    GES
    0.93
    OTS
    0.92
    PPS
    0.91
    ses
    0.90
    APIS
    0.90
     TAS
    0.90
    CTS
    0.89
    Activations Density 1.632%

    No Known Activations