© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13911
    Prev
    Next
    INDEX
    Explanations

    references to card games and related terminology

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

    the word "card"

    np_acts-logits-general · gemini-2.0-flash

    card and candidate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     EconPapers
    -0.55
    mostra
    -0.54
     Stephenson
    -0.44
     uses
    -0.44
     the
    -0.42
     habr
    -0.41
    rimento
    -0.41
     {}));
    -0.40
    DebuggerNonUser
    -0.39
    adpleegd
    -0.39
    POSITIVE LOGITS
     card
    1.43
     Card
    1.40
     Cards
    1.39
    Card
    1.35
     cards
    1.31
    Cards
    1.30
     CARDS
    1.23
     CARD
    1.20
    card
    1.19
    CARD
    1.13
    Activations Density 0.116%

    No Known Activations