© 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. 13133
    Prev
    Next
    INDEX
    Explanations

    terms related to ethical approval and consent in research studies

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

    preceding specific legal, ethical, or technical terms

    np_acts-logits-general · gemini-2.0-flash

    timely appeal, consent form, reagent grade

    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
    IntoConstraints
    -0.70
    transQ
    -0.54
    orsese
    -0.49
    styleable
    -0.47
    $_['
    -0.47
    SuspendLayout
    -0.44
     marchandises
    -0.43
     المعيارى
    -0.43
     transférez
    -0.42
    Kanpo
    -0.42
    POSITIVE LOGITS
    AutoField
    0.76
    invokeLater
    0.60
     NSCoder
    0.59
     Paglinawan
    0.59
    mybatisplus
    0.53
    Obrázky
    0.51
    Activités
    0.48
    UseVisualStyle
    0.47
    hyrchwyd
    0.46
    Šaltiniai
    0.46
    Activations Density 0.494%

    No Known Activations