© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 237
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formulas involving variables and operators

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

    LaTeX math mode expressions

    np_acts-logits-general · gemini-2.0-flash

    math symbols and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.75
    WebVitals
    -0.62
    UserScript
    -0.61
    apnews
    -0.56
     typelib
    -0.55
    ंदीखरीदारी
    -0.54
    ContentAsync
    -0.52
     kasarigan
    -0.49
    المشاركات
    -0.49
     يتيمه
    -0.49
    POSITIVE LOGITS
     gynnwys
    0.72
    mappedBy
    0.72
    ่านั้น
    0.62
     تانيه
    0.61
    Obrázky
    0.59
    stood
    0.59
    rawDesc
    0.56
    actylus
    0.56
     pinulongan
    0.56
     وتسجيلات
    0.55
    Activations Density 1.547%

    No Known Activations