© 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-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8940
    Prev
    Next
    INDEX
    Explanations

    terms related to competitive sports and tactical assessments of teams and players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.49
     AssemblyCulture
    -0.47
    UrlResolution
    -0.45
    IsContent
    -0.41
    GEBURTSDATUM
    -0.40
     exces
    -0.39
     considérons
    -0.39
    ConstraintMaker
    -0.39
    setViewName
    -0.39
    ungle
    -0.38
    POSITIVE LOGITS
     opponent
    0.76
     opponents
    0.68
     foes
    0.60
     enemy
    0.59
     musuh
    0.57
    Opponent
    0.56
     rivals
    0.56
     rivales
    0.54
     foe
    0.54
    opponent
    0.54
    Activations Density 0.407%

    No Known Activations