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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10653
    Prev
    Next
    INDEX
    Explanations

    terms related to auction details and buyer obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     coscienza
    -0.51
    AddTagHelper
    -0.49
     חיצוניים
    -0.48
    ագրություններ
    -0.47
     diapers
    -0.46
    nestjs
    -0.46
    migrationBuilder
    -0.44
    insular
    -0.43
    Sharing
    -0.43
     Embedding
    -0.43
    POSITIVE LOGITS
     auction
    2.14
     bidding
    2.05
     bid
    1.96
     bids
    1.84
     auctions
    1.84
     bidders
    1.83
     Auction
    1.80
     bidder
    1.75
    Auction
    1.74
    auction
    1.72
    Activations Density 0.100%

    No Known Activations