© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 42178
    Prev
    Next
    INDEX
    Explanations

    technical terms and function calls related to handling requests in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCreateView
    -0.35
     createSlice
    -0.34
    ValueStyle
    -0.32
    SEMICOLON
    -0.31
    (":");
    -0.30
    Predecesor
    -0.30
    Tikang
    -0.29
    licone
    -0.29
    }`).
    -0.29
    ="@
    -0.28
    POSITIVE LOGITS
     defaultstate
    0.61
    󠁢
    0.60
    makeText
    0.60
     pageContext
    0.57
    istoitu
    0.57
     informée
    0.56
     ModelExpression
    0.55
     المعيارى
    0.55
    barung
    0.54
     للمعارف
    0.53
    Activations Density 0.000%

    No Known Activations