© 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. 10-GEMMASCOPE-RES-16K
    6. 1847
    Prev
    Next
    INDEX
    Explanations

    programming and coding syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.57
     isNameExpr
    -0.50
     وتسجيلات
    -0.49
     GenerationType
    -0.48
    CloseOperation
    -0.48
    ?«
    -0.47
     Wikimedijinoj
    -0.46
    webElementXpaths
    -0.44
    AnchorStyles
    -0.44
    UseVisualStyle
    -0.43
    POSITIVE LOGITS
    Chham
    0.62
    getMock
    0.57
    koc
    0.55
    tighets
    0.55
    pulo
    0.55
    WebElementEntity
    0.54
    リート
    0.54
     propósito
    0.52
    uedes
    0.52
    mith
    0.51
    Activations Density 0.575%

    No Known Activations