© 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. 13975
    Prev
    Next
    INDEX
    Explanations

    references to successful business practices and traits of effective companies

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

    preceding modals ("can", "should", "must")

    np_acts-logits-general · gemini-2.0-flash

    good companies invest

    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
     ویکی‌پدیای
    -0.38
    RRect
    -0.36
     пото
    -0.35
     halide
    -0.35
     BROTHER
    -0.35
     BROTHERS
    -0.35
     Motos
    -0.34
     Пото
    -0.34
     crash
    -0.33
     HÀ
    -0.33
    POSITIVE LOGITS
    migrationBuilder
    0.53
    majánló
    0.52
     buoni
    0.51
     riusc
    0.48
    səhifə
    0.47
     financière
    0.47
     säll
    0.47
    stateProvider
    0.46
    出版年
    0.45
     vermogen
    0.45
    Activations Density 0.283%

    No Known Activations