© 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. 9-GEMMASCOPE-RES-131K
    11. 38813
    Prev
    Next
    INDEX
    Explanations

    terms related to epiphysis and related conditions

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

    epi- prefix, epiphyseal, epidural, Epifluorescence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.60
     وتسجيلات
    -0.56
    SqlClient
    -0.56
     pleaſure
    -0.53
     ſte
    -0.53
    ſelf
    -0.52
     ſtre
    -0.52
     uſe
    -0.50
    انتهای
    -0.50
    stylers
    -0.50
    POSITIVE LOGITS
     Epi
    2.03
     epi
    2.00
    Epi
    1.96
    epi
    1.87
    EPI
    1.16
    phany
    0.88
     Epif
    0.79
    エピ
    0.77
    epis
    0.72
     epis
    0.69
    Activations Density 0.011%

    No Known Activations