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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 30764
    Prev
    Next
    INDEX
    Explanations

    references to political campaigns and elections

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

    campaigns and revolutions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    AsUp
    -0.60
     Signalez
    -0.50
     dimaksud
    -0.46
     MenuView
    -0.45
    Xna
    -0.44
     camiset
    -0.43
     embaj
    -0.43
    点此举报
    -0.41
    MemoryWarning
    -0.39
    LayoutParams
    -0.39
    POSITIVE LOGITS
     combineReducers
    0.43
     Candidates
    0.39
    candidate
    0.39
     swe
    0.38
    CAND
    0.38
    失礼
    0.38
     CAND
    0.37
     Coat
    0.37
    incoming
    0.36
     ashore
    0.36
    Activations Density 0.056%

    No Known Activations