© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81714
    Prev
    Next
    INDEX
    Explanations

    instances or mentions of danger, near misses, and mortality

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

    near death or destruction

    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
     gekomen
    -0.34
     myö
    -0.31
     definitely
    -0.31
     sicuramente
    -0.30
     torebka
    -0.29
     niemals
    -0.28
     giras
    -0.28
     firmado
    -0.27
     definitively
    -0.27
     pewno
    -0.27
    POSITIVE LOGITS
    awtextra
    0.77
     تضيفلها
    0.67
     autorytatywna
    0.66
    setVerticalGroup
    0.64
    يميديا
    0.60
    ModelAdmin
    0.59
     beginnetje
    0.58
    Almost
    0.57
    Personensuche
    0.57
    almost
    0.57
    Activations Density 0.155%

    No Known Activations