© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1591
    Prev
    Next
    INDEX
    Explanations

    modal verbs and expressions of possibility or necessity

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

    Follows modal verbs (will, should, could, would)

    np_acts-logits-general · gemini-2.0-flash

    modal verbs expressing possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    un
    -0.40
    in
    -0.39
      
    -0.39
    部
    -0.39
    ↵↵
    -0.38
    The
    -0.37
    is
    -0.37
    p
    -0.37
     
    -0.36
    ↵
    -0.35
    POSITIVE LOGITS
     مرئيه
    0.69
    Personendaten
    0.68
     Paglinawan
    0.68
     ddelwed
    0.67
     ویکی‌پدی
    0.65
    adaptiveStyles
    0.65
    WebElementEntity
    0.63
    ſicht
    0.63
    ollary
    0.59
    Manbalar
    0.59
    Activations Density 1.010%

    No Known Activations