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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13272
    Prev
    Next
    INDEX
    Explanations

    references to motorsport and racing events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following racing locations or circuits

    np_acts-logits-general · gemini-2.0-flash

    racing circuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     van
    -0.55
    dafx
    -0.54
    المناصب
    -0.54
    LookAnd
    -0.54
     boat
    -0.50
    новништво
    -0.50
    parsedMessage
    -0.49
     Serikat
    -0.49
    ngdoc
    -0.48
    ніципалі
    -0.45
    POSITIVE LOGITS
     track
    1.11
     tracks
    1.08
    Track
    0.84
    track
    0.82
     TRACK
    0.82
     tracci
    0.82
    tracks
    0.80
     Track
    0.78
     Tracks
    0.76
    TRACK
    0.75
    Activations Density 0.141%

    No Known Activations