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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 274
    Prev
    Next
    INDEX
    Explanations

    entities related to establishments and businesses

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

    business and commercial establishments or locations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    fangen
    -0.31
     vectorielles
    -0.30
     framför
    -0.28
    msub
    -0.28
     разби
    -0.28
    ней
    -0.27
    เช่น
    -0.27
     pursuit
    -0.27
     اقت
    -0.26
     abstract
    -0.26
    POSITIVE LOGITS
     restaurant
    0.82
     shop
    0.81
    ร้าน
    0.78
     eatery
    0.77
    店
    0.77
     tavern
    0.76
     restaurants
    0.76
     Restaurant
    0.75
     cafe
    0.75
     shops
    0.71
    Activations Density 0.121%

    No Known Activations