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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2003
    Prev
    Next
    INDEX
    Explanations

    references to card games, specifically the game Gin Rummy and its mechanics

    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
    ConstraintMaker
    -0.67
     ddelweddau
    -0.63
    Étymologie
    -0.63
     ObjectParameter
    -0.60
     createState
    -0.59
    contentLoaded
    -0.57
    parsedMessage
    -0.57
    HomeAsUpEnabled
    -0.57
    yntaxException
    -0.57
     surla
    -0.55
    POSITIVE LOGITS
     card
    2.98
     cards
    2.91
     Card
    2.69
     Cards
    2.62
    card
    2.59
    Card
    2.58
    cards
    2.48
     CARD
    2.44
    Cards
    2.43
    CARD
    2.31
    Activations Density 0.148%

    No Known Activations