© 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
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 14904
    Prev
    Next
    INDEX
    Explanations

    patterns and numeric sequences related to coding or programming with focus on values and formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisSize
    -0.69
     ویکی‌پدی
    -0.68
    fjspx
    -0.68
    oa̍t
    -0.65
     '\\;'
    -0.63
    jsxFileName
    -0.63
    ➟
    -0.63
    MigrationBuilder
    -0.62
    IndentedString
    -0.61
    AutoScaleMode
    -0.61
    POSITIVE LOGITS
    1
    1.03
    １
    0.54
     ১
    0.50
    หนึ่ง
    0.43
     one
    0.39
     הראשון
    0.38
    ¹
    0.38
    ۱
    0.37
     १
    0.37
    ১
    0.35
    Activations Density 1.963%

    No Known Activations