© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3804
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to quizzes and assessment-related content

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

    Quiz-related words

    np_acts-logits-general · gemini-2.0-flash

    quiz questions

    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
    WEBPACK
    -0.42
    AttributeSet
    -0.34
    Бележки
    -0.30
     Kontakte
    -0.30
     Aktion
    -0.29
    Geplaatst
    -0.29
    єра
    -0.29
     världen
    -0.28
     AutoMapper
    -0.28
    packages
    -0.28
    POSITIVE LOGITS
     quiz
    1.08
     Quiz
    1.00
     quizzes
    0.88
    quiz
    0.87
     QUIZ
    0.86
    Quiz
    0.86
     trivia
    0.75
     Trivia
    0.73
     Quizzes
    0.73
     questions
    0.69
    Activations Density 0.284%

    No Known Activations