© 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. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105497
    Prev
    Next
    INDEX
    Explanations

    legal doctrines and principles, particularly those related to immunity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     exécu
    -0.59
     chrétien
    -0.46
     extranjero
    -0.43
     desconocido
    -0.42
     industriel
    -0.38
     inconnu
    -0.37
     Lingkungan
    -0.37
     ennemi
    -0.37
     asuntos
    -0.36
     canadien
    -0.36
    POSITIVE LOGITS
     BoxFit
    0.86
    AxisAlignment
    0.77
    ValueStyle
    0.74
     onCancelled
    0.72
    styleType
    0.71
    featureID
    0.65
    DeleteBehavior
    0.63
    OGND
    0.62
    AnchorStyles
    0.61
    InitVars
    0.61
    Activations Density 0.141%

    No Known Activations