© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15409
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and data manipulation commands

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

    Currency amounts and totals

    np_acts-logits-general · gemini-2.0-flash

    monetary amounts and prices

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    readdir
    -0.48
    igneur
    -0.47
    jois
    -0.46
     clave
    -0.46
     segu
    -0.44
     vocales
    -0.43
    ässer
    -0.42
    \}^{
    -0.41
     길
    -0.41
    trás
    -0.40
    POSITIVE LOGITS
     amount
    1.03
     SafeMath
    0.97
     monetary
    0.94
    amount
    0.93
     BigDecimal
    0.92
     amounts
    0.91
     dollars
    0.90
     Amount
    0.89
    Amount
    0.86
     dollar
    0.85
    Activations Density 0.145%

    No Known Activations