© 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 - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 3143
    Prev
    Next
    INDEX
    Explanations

    instances of legal or criminal incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (!__
    -0.41
    slidesToShow
    -0.36
     øns
    -0.36
    Personensuche
    -0.32
    ">)</
    -0.31
    horabuena
    -0.31
     sebelah
    -0.30
    JsonValue
    -0.29
    SpringRunner
    -0.29
    답
    -0.29
    POSITIVE LOGITS
     incident
    2.53
     incidents
    2.23
    incident
    2.03
     Incident
    1.98
     incidente
    1.81
     Incidents
    1.80
     kejadian
    1.63
    Incident
    1.62
    事件
    1.54
     घटना
    1.42
    Activations Density 0.667%

    No Known Activations