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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13455
    Prev
    Next
    INDEX
    Explanations

    positive attributes related to sports performance and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.84
    enumi
    -0.68
    
    -0.65
    tagHelperRunner
    -0.62
    ViewImports
    -0.61
    MigrationBuilder
    -0.59
     NSCoder
    -0.59
     getItemId
    -0.58
     الحره
    -0.58
     ویکی‌پدیا
    -0.57
    POSITIVE LOGITS
     brotherhood
    0.61
     mentality
    0.61
    cipl
    0.61
     hustle
    0.58
     sponges
    0.56
     ethic
    0.56
     compete
    0.56
     accountability
    0.55
     teammates
    0.55
     team
    0.55
    Activations Density 0.148%

    No Known Activations