© 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. 31-GEMMASCOPE-RES-131K
    6. 10054
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Button" and variations of it in code or documentations

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

    UI components and user prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Keuangan
    -0.40
     oleju
    -0.39
    kesan
    -0.38
     razonable
    -0.37
    ImageContext
    -0.37
     EconPapers
    -0.36
    typeparam
    -0.35
    ۜ
    -0.35
    闪过
    -0.35
     nocturno
    -0.35
    POSITIVE LOGITS
    bootstrapcdn
    0.70
     button
    0.60
     btn
    0.60
     BTN
    0.60
     defaultstate
    0.59
     initComponents
    0.58
     Button
    0.56
     Btn
    0.53
     Normdatei
    0.52
    ScopeManager
    0.50
    Activations Density 0.003%

    No Known Activations