© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5867
    Prev
    Next
    INDEX
    Explanations

    specific abbreviations and acronyms related to scientific and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -1.04
     ModelExpression
    -0.77
    UrlResolution
    -0.76
     resourceCulture
    -0.73
     itſelf
    -0.71
     ویکی‌پدیای
    -0.70
     AssemblyProduct
    -0.69
    HtmlAttribute
    -0.69
     Theſe
    -0.67
     насељу
    -0.66
    POSITIVE LOGITS
    раздо
    0.51
     soutien
    0.47
     出版
    0.47
    пол
    0.45
    надцать
    0.43
    C
    0.41
    laug
    0.41
     anbef
    0.40
    this
    0.40
    Legende
    0.40
    Activations Density 0.414%

    No Known Activations