© 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
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108118
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "juror" and related terms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Jur
    -1.88
    Jur
    -1.70
     jur
    -1.50
    jur
    -1.46
     JUR
    -1.31
     juror
    -0.95
     Jura
    -0.93
     jura
    -0.92
     jurors
    -0.91
    Jura
    -0.89
    POSITIVE LOGITS
    Obrázky
    0.48
     indietro
    0.41
    EndContext
    0.40
    noons
    0.38
     desierto
    0.37
    nodoc
    0.36
     settimane
    0.36
     Nachfrage
    0.36
     mxArray
    0.35
    OuterAlt
    0.34
    Activations Density 0.003%

    No Known Activations