© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15363
    Prev
    Next
    INDEX
    Explanations

    HTML formatting and content that signifies structure or separation in text

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

    Within HTML or LaTeX-style formatting

    np_acts-logits-general · gemini-2.0-flash

    media and technical terms

    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
    AndEndTag
    -0.51
    ward
    -0.51
    GEBURTSDATUM
    -0.49
    zadas
    -0.49
    tron
    -0.48
     ModelExpression
    -0.46
    èdia
    -0.46
    SwingConstants
    -0.46
    rån
    -0.45
    ffilm
    -0.45
    POSITIVE LOGITS
     chré
    0.71
     Audiodateien
    0.69
     ویکی‌آمباردا
    0.68
    CloseOperation
    0.65
    ')";
    0.59
    usepackage
    0.58
     odkazy
    0.56
    <blockquote>
    0.56
     occidentale
    0.55
    </blockquote>
    0.54
    Activations Density 0.034%

    No Known Activations