© 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. 58967
    Prev
    Next
    INDEX
    Explanations

    concepts and phrases associated with safety and its related importance

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

    safety concerns and features

    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
     wireType
    -0.68
    InitVars
    -0.48
     endwhile
    -0.48
    addPreferredGap
    -0.47
     typewriter
    -0.46
     الحره
    -0.45
    المناصب
    -0.44
    windowFixed
    -0.44
    engesch
    -0.44
    ellem
    -0.44
    POSITIVE LOGITS
    Safety
    1.11
     safety
    1.09
     sécurité
    1.06
     seguridad
    1.04
     Safety
    1.02
    safety
    1.02
     Sicherheit
    0.98
    Security
    0.96
     segurança
    0.95
     SAFETY
    0.94
    Activations Density 0.035%

    No Known Activations