© 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. 104962
    Prev
    Next
    INDEX
    Explanations

    phrases indicating inadequacy or insufficiency in explanations or solutions

    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
    chufe
    -0.47
    ficie
    -0.44
     noqa
    -0.44
     bezeichneter
    -0.44
    PositiveButton
    -0.42
    parseFrom
    -0.41
     CONC
    -0.41
    pective
    -0.40
    RRect
    -0.40
     useStyles
    -0.40
    POSITIVE LOGITS
     kræ
    0.45
    protoimpl
    0.41
     suffice
    0.40
    ]){
    0.38
    __.__
    0.37
     sufficient
    0.36
    MigrationBuilder
    0.36
     sufficiente
    0.36
     Sicherung
    0.36
    TagMode
    0.36
    Activations Density 0.111%

    No Known Activations