© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 3974
    Prev
    Next
    INDEX
    Explanations

    questions or references related to insurance matters and vehicle incidents

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    insurance or insurers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    setLayoutManager
    -0.66
     Sebastián
    -0.65
    GeoNames
    -0.65
     Argonne
    -0.65
     Sado
    -0.63
     Magdeburg
    -0.58
    IBarButtonItem
    -0.57
     ioutil
    -0.57
     Hawthorne
    -0.56
    JpaRepository
    -0.56
    POSITIVE LOGITS
     insurance
    2.29
     Insurance
    2.10
    Insurance
    1.98
     insurer
    1.98
    insurance
    1.92
     insurers
    1.90
     INSURANCE
    1.84
     insured
    1.67
     Versicher
    1.47
    保险
    1.39
    Activations Density 0.029%

    No Known Activations