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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7940
    Prev
    Next
    INDEX
    Explanations

    structure and details related to sports tournaments

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

    Tournament or sports competition

    np_acts-logits-general · gemini-2.0-flash

    round robin system

    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
     auprès
    -0.57
    Autoritní
    -0.55
    SharedCtor
    -0.53
     apprendre
    -0.48
     récentes
    -0.48
     homicidio
    -0.48
     rubia
    -0.47
     personnelle
    -0.47
     recentes
    -0.46
    блемы
    -0.45
    POSITIVE LOGITS
     matchups
    0.93
     matches
    0.92
     tournament
    0.90
     playoffs
    0.88
     competition
    0.84
     winners
    0.84
     playoff
    0.83
     finals
    0.83
     format
    0.81
     contestants
    0.80
    Activations Density 0.241%

    No Known Activations