© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7789
    Prev
    Next
    INDEX
    Explanations

    descriptions of injuries or physical harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attract
    -0.36
     MainAxisSize
    -0.35
     postav
    -0.35
     respiración
    -0.35
     Conſ
    -0.35
     fantasmas
    -0.35
    ictwo
    -0.34
    рад
    -0.33
    tschafts
    -0.33
    wanderung
    -0.32
    POSITIVE LOGITS
    Injury
    0.64
     resourceCulture
    0.63
    MigrationBuilder
    0.62
     abrasion
    0.61
     bashing
    0.60
     smashing
    0.60
     bruise
    0.60
     Injury
    0.60
     onBackPressed
    0.59
    injury
    0.58
    Activations Density 0.330%

    No Known Activations