© 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. 22-GEMMASCOPE-RES-16K
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    information related to sports achievements and events

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

    tournaments or tours

    np_acts-logits-general · gemini-2.0-flash

    sports tours and tournaments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Faust
    -0.57
     club
    -0.56
     clubs
    -0.55
    WidgetItem
    -0.55
     NSCoder
    -0.55
    razos
    -0.53
    存于互联网档案馆
    -0.52
     BorderRadius
    -0.52
     Wimbledon
    -0.51
     Clubs
    -0.50
    POSITIVE LOGITS
     tour
    0.85
     Tour
    0.73
     TOUR
    0.71
    tableFuture
    0.68
    Tour
    0.66
     tours
    0.63
    tour
    0.61
     Tours
    0.60
    tours
    0.58
     AssemblyCulture
    0.57
    Activations Density 0.099%

    No Known Activations