© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 421
    Prev
    Next
    INDEX
    Explanations

    specific openings or headers in a document

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

    numeric codes or references in a technical context

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

    numbers and codes

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     onCancelled
    -0.74
     تضيفلها
    -0.73
     ویکی‌پدیا
    -0.69
    RegressionTest
    -0.69
    Билгалдахарш
    -0.68
    Cyfeiriadau
    -0.63
    AddHtmlAttribute
    -0.63
     <=",
    -0.59
    Rujuakan
    -0.59
    XmlAccessorType
    -0.58
    POSITIVE LOGITS
    ylase
    0.59
    StoryboardSegue
    0.58
     RCP
    0.56
    0
    0.55
     GDR
    0.53
     heureux
    0.52
     impermeable
    0.52
    rungsseite
    0.52
    _
    0.51
    2
    0.49
    Activations Density 0.016%

    No Known Activations