© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 8359
    Prev
    Next
    INDEX
    Explanations

    incidents related to competitive racing events and their outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    car accidents and malfunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Autorisations
    -0.54
     protoimpl
    -0.53
     Réponses
    -0.51
     contextLoads
    -0.50
    +#+
    -0.49
     Chwiliwch
    -0.48
    Aholisi
    -0.48
    MeasureSpec
    -0.47
    tangentMode
    -0.46
    redient
    -0.45
    POSITIVE LOGITS
     mishap
    0.68
     debris
    0.65
     unlucky
    0.63
     crashed
    0.61
     damaged
    0.58
     disastrous
    0.57
     crash
    0.57
     misfortune
    0.57
     incident
    0.56
     accidents
    0.56
    Activations Density 0.020%

    No Known Activations