© 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. 9-GEMMASCOPE-RES-131K
    11. 38891
    Prev
    Next
    INDEX
    Explanations

    references to physical impacts or assaults

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

    being hit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brida
    -0.42
    wikk
    -0.40
     arşivlendi
    -0.40
     wypo
    -0.40
     CDP
    -0.38
     RDA
    -0.38
    Portale
    -0.38
    TEMPLATE
    -0.37
     route
    -0.37
    󠁢
    -0.36
    POSITIVE LOGITS
    punch
    0.54
    Hit
    0.54
     hit
    0.52
     punches
    0.50
    edipus
    0.50
    Hits
    0.49
     heridos
    0.49
     PUNCH
    0.49
     hits
    0.49
     golpea
    0.48
    Activations Density 0.022%

    No Known Activations