© 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. 20-GEMMASCOPE-RES-131K
    11. 116845
    Prev
    Next
    INDEX
    Explanations

    language related to body language and nonverbal communication cues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    OGND
    -0.65
    principalColumn
    -0.58
     /\.
    -0.58
    extAlignment
    -0.56
    AutoScaleMode
    -0.55
     సౌకర్య
    -0.54
    Autoritní
    -0.52
     مرئيه
    -0.52
    WindowConstants
    -0.52
    :✨
    -0.51
    POSITIVE LOGITS
    LabelTagHelper
    0.43
     Paulista
    0.37
     Possession
    0.36
     descriptive
    0.36
     possession
    0.36
    дава
    0.36
     commented
    0.35
    その
    0.35
    Poss
    0.35
     ven
    0.35
    Activations Density 0.089%

    No Known Activations