© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15870
    Prev
    Next
    INDEX
    Explanations

    statistical data and player performance metrics in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparencia
    -0.32
     plumas
    -0.31
     planificación
    -0.31
     Turquía
    -0.30
     Experten
    -0.30
     persönliche
    -0.29
     récon
    -0.29
     Weisheit
    -0.29
     žel
    -0.28
     acto
    -0.28
    POSITIVE LOGITS
     MLS
    0.87
    MLS
    0.78
     soccer
    0.77
     noDo
    0.75
    Soccer
    0.73
     Soccer
    0.71
    soccer
    0.69
    kloped
    0.68
     Roskov
    0.65
    存于互联网档案馆
    0.64
    Activations Density 0.260%

    No Known Activations