© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    terminology related to educational and medical staff within a community or institution

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

    administrative support staff

    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
     kaynağından
    -0.56
    تقاوى
    -0.55
     فريبيس
    -0.54
    NameInMap
    -0.52
     propOrder
    -0.51
    出版年
    -0.51
    Rüyada
    -0.49
    addGap
    -0.49
     Signalez
    -0.48
    BufferException
    -0.47
    POSITIVE LOGITS
     support
    1.37
    support
    1.32
    Support
    1.24
     Support
    1.23
     SUPPORT
    1.17
     administrative
    1.16
    SUPPORT
    1.15
     staff
    1.05
     supporting
    1.05
    administrative
    1.00
    Activations Density 0.116%

    No Known Activations