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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 35904
    Prev
    Next
    INDEX
    Explanations

    specific references to Chinese cuisine and notable figures in Chinese art

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Chinese surnames and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
     resourceCulture
    -0.65
     Infórmanos
    -0.55
    󠁣
    -0.53
     مرئيه
    -0.52
    ementara
    -0.51
    Diweddarwch
    -0.50
    RTEX
    -0.50
    ressee
    -0.50
    */),
    -0.49
    POSITIVE LOGITS
    FetchType
    0.33
     mob
    0.31
    priv
    0.29
    requipa
    0.28
     const
    0.28
    const
    0.28
    mathop
    0.28
    PrivateRoute
    0.28
     Priv
    0.28
     mobili
    0.27
    Activations Density 0.088%

    No Known Activations