© 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. 3-GEMMASCOPE-RES-16K
    6. 5709
    Prev
    Next
    INDEX
    Explanations

    sections of the document related to HTML headers and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.79
    المشاركات
    -0.60
     mergeFrom
    -0.56
    تفصیلات
    -0.53
    Hentet
    -0.52
     Lauter
    -0.52
     ligiloj
    -0.52
    XmlEnum
    -0.51
     anglès
    -0.50
     newBuilder
    -0.47
    POSITIVE LOGITS
     ویکی‌پدیای
    0.78
    <h2>
    0.72
    setupUi
    0.70
     fű
    0.64
    HEAST
    0.62
    setViewName
    0.61
    
    0.61
    InSection
    0.58
    بوابة
    0.58
    Assembly
    0.56
    Activations Density 0.088%

    No Known Activations