© 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. 20-GEMMASCOPE-RES-16K
    6. 15204
    Prev
    Next
    INDEX
    Explanations

    special formatting or markup elements in a document, indicating emphasis or structure

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

    Bolded tokens: titles, section headings, or emphasis

    np_acts-logits-general · gemini-2.0-flash

    section titles and headings

    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
    حوالہ
    -0.73
    NewUrlParser
    -0.70
    Tikang
    -0.69
     للمعارف
    -0.67
    istoitu
    -0.67
     وتسجيلات
    -0.67
    Cyfeiriadau
    -0.67
    queryInterface
    -0.64
    initializeApp
    -0.64
    IComponent
    -0.64
    POSITIVE LOGITS
    ↵
    0.91
    ↵↵
    0.83
    <strong>
    0.65
    ↵↵↵
    0.57
     -
    0.55
    <b>
    0.54
    :
    0.52
    </h2>
    0.50
    </h5>
    0.50
    </h3>
    0.48
    Activations Density 0.084%

    No Known Activations