© 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. 37-GEMMASCOPE-RES-16K
    11. 7421
    Prev
    Next
    INDEX
    Explanations

    indicators of performance in competitive contexts, particularly in elections and races

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fuel
    -0.32
    fuel
    -0.31
     Fuel
    -0.31
    Fre
    -0.31
     Fre
    -0.30
     plantilla
    -0.30
     Freedman
    -0.30
     neón
    -0.30
    FLICT
    -0.29
    fre
    -0.29
    POSITIVE LOGITS
     finish
    2.84
     Finish
    2.55
    finish
    2.55
     finishing
    2.48
     FINISH
    2.47
     finishes
    2.45
    Finish
    2.41
     finished
    2.34
     finisher
    2.28
     finis
    2.25
    Activations Density 0.651%

    No Known Activations