© 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. 31-GEMMASCOPE-RES-131K
    11. 12116
    Prev
    Next
    INDEX
    Explanations

    references to yogurt and its consumption

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

    yogurt and probiotics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.54
    !*\
    -0.47
    ceiro
    -0.46
    phic
    -0.45
    æld
    -0.41
     Halley
    -0.41
    nste
    -0.41
    letch
    -0.41
    fey
    -0.40
    GRESS
    -0.39
    POSITIVE LOGITS
     yogurt
    1.38
     yoghurt
    1.20
     Yogurt
    1.18
    Yogurt
    1.17
     yogur
    1.00
    yog
    0.91
     yog
    0.89
    ghurt
    0.87
     dairy
    0.77
    ヨーグルト
    0.77
    Activations Density 0.032%

    No Known Activations