© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 43261
    Prev
    Next
    INDEX
    Explanations

    words that indicate revelation or disclosure

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

    making things known

    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
     companyId
    -0.66
     katze
    -0.63
     createdBy
    -0.60
    Goose
    -0.57
    stylers
    -0.56
    itemType
    -0.55
    Rye
    -0.55
    Tanger
    -0.55
     orderId
    -0.52
    IBarButtonItem
    -0.52
    POSITIVE LOGITS
     reveal
    1.16
     reveals
    1.08
    reveal
    1.06
     revealed
    1.02
     revealing
    1.01
     Reveal
    0.98
    Reveal
    0.96
     Reveals
    0.90
     Revealed
    0.83
     revelar
    0.81
    Activations Density 0.020%

    No Known Activations