© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 10444
    Prev
    Next
    INDEX
    Explanations

    terms related to sports team victories and ethnic diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.35
    TEntity
    -0.31
     Coss
    -0.29
     Guanajuato
    -0.28
     az
    -0.27
    oare
    -0.27
    misc
    -0.27
    migrationBuilder
    -0.26
    xem
    -0.26
    NESOTA
    -0.26
    POSITIVE LOGITS
     Fiji
    1.15
    Fiji
    1.09
     Fij
    1.01
     Ratu
    0.74
     Vanuatu
    0.73
     fij
    0.71
     Samoa
    0.71
    斐
    0.71
     Pacific
    0.70
     Viti
    0.70
    Activations Density 0.110%

    No Known Activations