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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6338
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental or organizational oversight and regulatory frameworks

    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
     Sociedade
    -0.61
     ayuntamiento
    -0.57
     maire
    -0.56
    нівер
    -0.55
     Ayuntamiento
    -0.54
     شهرداری
    -0.53
    CLUB
    -0.53
     club
    -0.53
    apimachinery
    -0.52
     Club
    -0.52
    POSITIVE LOGITS
     Division
    0.84
    Division
    0.77
     division
    0.77
     Directorate
    0.75
     office
    0.72
     EconPapers
    0.71
     staff
    0.70
    division
    0.69
     agency
    0.68
     DIVISION
    0.67
    Activations Density 0.325%

    No Known Activations