© 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. 16289
    Prev
    Next
    INDEX
    Explanations

    terms and suffixes related to small decorative objects and diminutive forms

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

    diminutive suffixes and names

    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-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
    存于互联网档案馆
    -0.66
     ویکی‌پدیا
    -0.59
     alugar
    -0.56
     égard
    -0.53
    '])
    -0.52
     sustituir
    -0.49
    rsiniz
    -0.48
     climático
    -0.48
    ']))
    -0.47
     cuaca
    -0.47
    POSITIVE LOGITS
    nette
    0.62
    zette
    0.61
    Nicky
    0.58
    ette
    0.57
    chito
    0.57
    little
    0.57
    berger
    0.56
    netto
    0.55
    lette
    0.54
    chetto
    0.54
    Activations Density 0.016%

    No Known Activations