© 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. 1-GEMMASCOPE-RES-16K
    6. 14109
    Prev
    Next
    INDEX
    Explanations

    references to catalogs or cataloging processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.94
     ویکی‌پدیای
    -0.89
     CreateTagHelper
    -0.79
    TagMode
    -0.77
     Мексичка
    -0.76
    Ārējās
    -0.75
    帖最后由
    -0.73
    sizeCache
    -0.71
     AssemblyCulture
    -0.71
     Rtl
    -0.68
    POSITIVE LOGITS
     ing
    1.21
     catalog
    1.02
     Catalog
    0.96
    Catalog
    0.91
    catalog
    0.87
     Ing
    0.86
     catalogs
    0.86
     catalogue
    0.79
    Ing
    0.71
     CATALOG
    0.69
    Activations Density 0.065%

    No Known Activations