© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 128201
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate mathematical or scientific reasoning

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

    Because, Object, We, Suppose, Nova, Consider

    np_acts-logits-general · gemini-2.5-flash-lite

    section headings, titles, and other document-structure markers (e.g., underline/equals/dashes and caption/section labels).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     Wikimedijinoj
    -0.58
    цездатний
    -0.57
    TagMode
    -0.55
     nakalista
    -0.51
     فريبيس
    -0.50
    ⟬
    -0.50
     تضيفلها
    -0.50
     gynhyrchwyd
    -0.50
     الرياضيه
    -0.49
    aarrggbb
    -0.49
    POSITIVE LOGITS
    tawesome
    0.39
    DockStyle
    0.36
     안
    0.35
    OK
    0.35
    CHARGE
    0.34
    自
    0.33
    Anna
    0.33
    fortawesome
    0.32
     gewel
    0.32
    iment
    0.32
    Activations Density 0.262%

    No Known Activations