© 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. 17180
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "spill" associated with liquid incidents

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

    accidental spills and negative outcomes

    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
     surla
    -0.40
    QRect
    -0.40
     braccia
    -0.39
    nonatomic
    -0.38
    الدراسه
    -0.38
     gambe
    -0.37
     وتسجيلات
    -0.37
     Host
    -0.37
    RuleContext
    -0.36
     betrek
    -0.36
    POSITIVE LOGITS
    spill
    0.94
     Spill
    0.93
     spill
    0.92
    Spill
    0.92
     spills
    0.80
     spilling
    0.79
     spilled
    0.75
     spillage
    0.68
     spilt
    0.64
     derra
    0.55
    Activations Density 0.001%

    No Known Activations