© 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. 37272
    Prev
    Next
    INDEX
    Explanations

    various forms of parentheses and quotations used in a coding or data structure context

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

    configuration, parse, upload, capacity, data, function

    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
     Mitteln
    -0.56
     lisäksi
    -0.41
     edades
    -0.40
     fotográfico
    -0.40
     tiež
    -0.40
      
    -0.39
     literario
    -0.39
     húmedo
    -0.39
     dioses
    -0.38
     Gesetze
    -0.38
    POSITIVE LOGITS
    webElementXpaths
    1.05
     autorytatywna
    0.91
    цездатний
    0.87
    Personendaten
    0.85
     ویکی‌پدی
    0.83
     kasarigan
    0.81
    :✨
    0.81
    Билгалдахарш
    0.81
    NameInMap
    0.79
    NUMX
    0.77
    Activations Density 0.115%

    No Known Activations