© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13020
    Prev
    Next
    INDEX
    Explanations

    information related to sports positions and player statistics

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

    football/soccer player position descriptions and defensive role terminology.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebElementEntity
    -0.38
    enterOuterAlt
    -0.36
    otrop
    -0.36
     dri
    -0.34
    XmlType
    -0.33
    Grou
    -0.33
     Grou
    -0.32
    SourceChecksum
    -0.32
     strike
    -0.32
    Dri
    -0.32
    POSITIVE LOGITS
     defence
    1.27
     defense
    1.25
     defender
    1.16
     defenders
    1.14
    Defence
    1.13
     Defense
    1.12
     Defence
    1.12
     défense
    1.12
    defense
    1.12
     defensa
    1.11
    Activations Density 0.113%

    No Known Activations