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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 10133
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and processes.

    oai_token-act-pair · gemini-1.5-flashTriggered by @bot

    words beginning with "son" or variations of "son", particularly in technical or scientific contexts like "sonography", "sonication", or names like "Sonia" or "Sonoran".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    references to ultrasound imaging and medical diagnostics involving the term "son"

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

    following "son"

    np_acts-logits-general · gemini-2.0-flash

    son and related words

    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
    SharedCtor
    -0.76
    modelBuilder
    -0.71
    BagLayout
    -0.71
     InputDecoration
    -0.66
    Istorija
    -0.66
     grigio
    -0.65
     ویکی‌پدیای
    -0.64
     Obrador
    -0.64
     noastră
    -0.62
    cshtml
    -0.59
    POSITIVE LOGITS
     SON
    0.77
     sons
    0.72
     Sons
    0.70
    iyor
    0.69
     Son
    0.68
    orous
    0.67
     Sonya
    0.64
     SONS
    0.63
    UGHTER
    0.63
    nets
    0.61
    Activations Density 0.077%

    No Known Activations