© 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. 28-GEMMASCOPE-RES-16K
    11. 11507
    Prev
    Next
    INDEX
    Explanations

    mentions of sports statistics and player performance

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

    sports players and/or games

    np_acts-logits-general · gemini-2.0-flash

    player performance statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    farande
    -0.39
    úgó
    -0.39
     الاطلاع
    -0.36
     procéder
    -0.34
    melen
    -0.34
     DAY
    -0.33
     <<<<<<<<<<<<<<
    -0.33
    uliert
    -0.32
     siang
    -0.32
     Rasen
    -0.32
    POSITIVE LOGITS
    SharedCtor
    0.66
    reportWebVitals
    0.58
     beginnetje
    0.55
    ArgsConstructor
    0.55
     AssemblyCulture
    0.53
     فريبيس
    0.51
    httphttps
    0.51
    CDCl
    0.49
     numerus
    0.49
     sumpay
    0.48
    Activations Density 0.294%

    No Known Activations