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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 63017
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structural elements typically used in product descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    +#+
    -0.55
    省市镇
    -0.48
    ViewImports
    -0.46
     Constructors
    -0.43
    hyrchwyd
    -0.43
    بوابة
    -0.42
    AddTagHelper
    -0.41
    angliski
    -0.41
    IsContent
    -0.41
     relief
    -0.41
    POSITIVE LOGITS
     auction
    0.64
    auction
    0.52
     Auction
    0.52
     auctions
    0.49
     eBay
    0.49
    拍卖
    0.47
    Auction
    0.47
     ebay
    0.46
     Ebay
    0.45
    eBay
    0.43
    Activations Density 0.019%

    No Known Activations