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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103784
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to scientific and mathematical measurements

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

    Technical terms or modifiers that provide precision in specialized academic, scientific or programming contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ipen
    -0.40
     general
    -0.36
    st
    -0.36
    Usa
    -0.35
     inherently
    -0.34
    pure
    -0.33
    დი
    -0.33
    man
    -0.33
    elab
    -0.32
     Oath
    -0.32
    POSITIVE LOGITS
     otomatig
    0.81
    GEBURTSDATUM
    0.73
    endphp
    0.70
     Paglinawan
    0.65
     ویکی‌پدی
    0.65
     المعيارى
    0.62
    XmlAccessorType
    0.59
    RenderAtEndOf
    0.59
     мәкал
    0.58
    AndEndTag
    0.57
    Activations Density 0.050%

    No Known Activations