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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14615
    Prev
    Next
    INDEX
    Explanations

    financial and monetary calculations involving currencies

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

    Calculations involving totals or amounts

    np_acts-logits-general · gemini-2.0-flash

    total 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 @ 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
    jois
    -0.58
     pinulongan
    -0.52
     clave
    -0.49
    (;;)
    -0.46
     calendriers
    -0.46
    igneur
    -0.45
     (;;)
    -0.45
    lau
    -0.45
    trás
    -0.44
    ophen
    -0.44
    POSITIVE LOGITS
     amount
    1.00
     total
    0.93
    total
    0.92
     calculated
    0.91
    amount
    0.89
     dollars
    0.89
     BigDecimal
    0.88
     amounts
    0.85
     decimal
    0.81
     Amount
    0.80
    Activations Density 0.096%

    No Known Activations