Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7957
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to sports performance

    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
    ConstraintMaker
    -0.41
     campeão
    -0.38
    rawDesc
    -0.35
    iertamente
    -0.32
    נצ
    -0.31
     vôtre
    -0.31
     consecutively
    -0.31
    Referencie
    -0.30
    Meta
    -0.30
     다음
    -0.30
    POSITIVE LOGITS
    GTCX
    0.79
    tagHelperRunner
    0.68
     effort
    0.62
    msgTypes
    0.57
    
    0.55
     appearance
    0.54
     efforts
    0.54
    effort
    0.54
     outing
    0.53
    webElement
    0.53
    Activations Density 0.218%

    No Known Activations