© 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. 69718
    Prev
    Next
    INDEX
    Explanations

    the Arabic letter "د" and its occurrences in punctuation

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

    da

    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
     informée
    -0.35
    emlrt
    -0.35
    TintMode
    -0.35
     sauter
    -0.35
     followers
    -0.33
    ‏‏
    -0.32
    RTLR
    -0.32
     kvä
    -0.32
     relativi
    -0.32
     Basta
    -0.32
    POSITIVE LOGITS
    DoubleQuotes
    0.63
     FetchType
    0.57
    :✨
    0.56
     responseData
    0.54
    ]-->
    0.53
     CascadeType
    0.52
    EndInit
    0.52
     GenerationType
    0.51
    ViewImports
    0.49
     וד
    0.49
    Activations Density 0.004%

    No Known Activations