© 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. 33-GEMMASCOPE-RES-16K
    11. 13497
    Prev
    Next
    INDEX
    Explanations

    achievements in athletics, specifically involving women's relay races and medals

    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
    znac
    -0.41
     fört
    -0.38
     FISHING
    -0.36
    RequiresApi
    -0.35
    GeoNames
    -0.35
     מיט
    -0.35
    useNewUrlParser
    -0.34
     PROTE
    -0.34
     hornear
    -0.34
     förb
    -0.33
    POSITIVE LOGITS
     relay
    0.90
     Relay
    0.82
     sprint
    0.77
     relays
    0.74
    Relay
    0.71
    relay
    0.70
     butterfly
    0.67
     Sprint
    0.66
     sprinter
    0.66
     races
    0.62
    Activations Density 0.086%

    No Known Activations