© 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. 13901
    Prev
    Next
    INDEX
    Explanations

    references to total quantities or measurements

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

    "total" and associated quantities

    np_acts-logits-general · gemini-2.0-flash

    total before a quantity

    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
     lámpara
    -0.59
     lâmpada
    -0.58
    sene
    -0.51
     manguera
    -0.51
    chambre
    -0.50
     impresora
    -0.49
    machines
    -0.49
    withIdentifier
    -0.49
     screwdriver
    -0.49
    changers
    -0.49
    POSITIVE LOGITS
     total
    1.29
    total
    1.23
     Total
    1.18
    Total
    1.17
     TOTAL
    1.02
    TOTAL
    1.01
    getTotal
    0.95
     setTotal
    0.95
     totals
    0.95
     getTotal
    0.93
    Activations Density 0.143%

    No Known Activations