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. 1638
    Prev
    Next
    INDEX
    Explanations

    starting points or introductions to new sections or topics in text

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

    after company or organization names

    np_acts-logits-general · gemini-2.0-flash

    legal, technical, or financial phrases

    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
    行政区划
    -0.61
    Geplaatst
    -0.53
    :✨
    -0.52
    untergang
    -0.52
     coloré
    -0.52
     "..\..\
    -0.49
     ObjectMapper
    -0.49
    ianas
    -0.48
    estacks
    -0.47
    بوابة
    -0.47
    POSITIVE LOGITS
    DataAnnotations
    0.57
    leps
    0.53
    ChildScrollView
    0.53
    RUnlock
    0.53
     carbon
    0.50
    belongs
    0.50
    HtmlAttribute
    0.50
     Toulon
    0.49
    AxisAlignment
    0.49
    principalColumn
    0.48
    Activations Density 0.059%

    No Known Activations