© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10176
    Prev
    Next
    INDEX
    Explanations

    references to yoga and related activities

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

    yoga, classes, and instructors

    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
    łbym
    -0.47
     saveiro
    -0.46
     stanovnika
    -0.46
     zijne
    -0.43
     ImGui
    -0.43
     kasarigan
    -0.42
     voedsel
    -0.42
     wezen
    -0.41
     anillos
    -0.41
     nucléaire
    -0.41
    POSITIVE LOGITS
     yoga
    1.29
    Yoga
    1.14
     Yoga
    1.14
    yoga
    1.04
     yog
    1.02
     YOGA
    0.96
    ヨガ
    0.88
    ulemon
    0.81
    瑜伽
    0.79
    🧘
    0.77
    Activations Density 0.012%

    No Known Activations