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. 4126
    Prev
    Next
    INDEX
    Explanations

    information related to numerical expressions and calculations involving prime factors

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

    after quotation marks or parentheses

    np_acts-logits-general · gemini-2.0-flash

    keywords and data types

    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
    TypedDataSet
    -0.70
     للاسماء
    -0.68
    windowFixed
    -0.68
    WithIOException
    -0.67
     tartalomajánló
    -0.67
    :✨
    -0.65
     مرئيه
    -0.62
     Réponses
    -0.62
    ()][
    -0.56
     kaarangay
    -0.56
    POSITIVE LOGITS
     Chwiliwch
    0.73
    こちらも
    0.72
    これも
    0.72
     …
    0.70
    ]--;
    0.67
    bootstrapcdn
    0.61
    ResumeLayout
    0.60
    ditto
    0.59
     Vikipedi
    0.59
     â
    0.59
    Activations Density 1.752%

    No Known Activations