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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 8150
    Prev
    Next
    INDEX
    Explanations

    terms related to counterfeit detection and anti-counterfeiting features in currency

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

    Currency, postage, and envelopes

    np_acts-logits-general · gemini-2.0-flash

    American coins and currency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.75
     MonoBehaviour
    -0.73
     Roskov
    -0.72
    migrationBuilder
    -0.71
    الحياه
    -0.68
    :✨
    -0.62
    WindowConstants
    -0.60
     ویکی‌پدیای
    -0.60
    Xiv
    -0.56
     surla
    -0.53
    POSITIVE LOGITS
     coins
    1.09
     coin
    1.08
     Coin
    0.92
    coin
    0.88
    Coin
    0.87
     Coins
    0.83
    coins
    0.82
     circulation
    0.81
     minted
    0.79
     COIN
    0.77
    Activations Density 0.093%

    No Known Activations