© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9307
    Prev
    Next
    INDEX
    Explanations

    instances of tricks or performances in an informal context

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

    dance and tricks

    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
     viewDidLoad
    -0.43
    latego
    -0.43
    VersionUID
    -0.41
    toprule
    -0.40
     panela
    -0.40
    لينكات
    -0.38
    dengar
    -0.38
    JAXB
    -0.38
     PrintWriter
    -0.37
    
    -0.37
    POSITIVE LOGITS
     dance
    1.35
     dances
    1.12
    dance
    1.07
     danced
    1.07
     Dance
    1.05
    Dance
    1.02
     DANCE
    1.02
     dança
    0.97
     dancing
    0.95
    DANCE
    0.89
    Activations Density 0.028%

    No Known Activations