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. 14531
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotation marks in the text

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

    Opening quotation marks

    np_acts-logits-general · gemini-2.0-flash

    quotations and punctuation

    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
     فريبيس
    -0.83
    ImageContext
    -0.72
     NSCoder
    -0.71
     ویکی‌پدیا
    -0.69
    Geplaatst
    -0.68
    InSection
    -0.68
     "
    -0.66
    findpost
    -0.61
    enumi
    -0.61
    ClientSize
    -0.61
    POSITIVE LOGITS
     Efq
    0.68
    MENAFN
    0.65
     uſed
    0.54
     Monfieur
    0.53
    atissimo
    0.53
     vacanze
    0.53
    
    0.52
    box
    0.51
     soprav
    0.51
     küche
    0.51
    Activations Density 0.231%

    No Known Activations