© 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. 44
    Prev
    Next
    INDEX
    Explanations

    complex phrasing indicative of uncertainty or the need for clarification

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

    write advice

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

    phrases expressing uncertainty, hedging, or inability to say/know (e.g., "hard to say," "without actual knowledge," "I do not know").

    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
     TÉCN
    -0.36
    holen
    -0.36
     Técnica
    -0.35
     Usaha
    -0.35
     Cientí
    -0.35
     Técnico
    -0.34
     Riau
    -0.34
    bricht
    -0.34
     gezet
    -0.34
     renovables
    -0.34
    POSITIVE LOGITS
     estekak
    0.63
     المعيارى
    0.52
     ujednoznacz
    0.52
    tvguidetime
    0.51
     ویکی‌پدی
    0.49
    ErrUnexpectedEOF
    0.47
    rungsseite
    0.46
    irvana
    0.46
     otomatig
    0.44
    responseText
    0.43
    Activations Density 0.064%

    No Known Activations