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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 46584
    Prev
    Next
    INDEX
    Explanations

    terms associated with non-toxic or non-hazardous materials

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

    negation prefix 'non'

    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
    Not in Any Lists

    No Comments

    Negative Logits
    näm
    -0.45
     Rich
    -0.42
     Gab
    -0.38
    Rich
    -0.34
    ...
    -0.33
     отлич
    -0.33
    urri
    -0.32
    嬉しい
    -0.32
    [
    -0.32
    價值
    -0.31
    POSITIVE LOGITS
     Савезне
    0.88
    ChildScrollView
    0.80
    featureID
    0.76
    EndContext
    0.75
    XmlAccessType
    0.74
    IntoConstraints
    0.74
    tagHelperRunner
    0.72
    новништво
    0.70
     Administrativna
    0.70
    ftagPool
    0.69
    Activations Density 0.044%

    No Known Activations