© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12158
    Prev
    Next
    INDEX
    Explanations

    structural elements and symbols related to programming or mathematical functions

    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
    :]:
    -0.27
     vertically
    -0.27
    ,'\
    -0.25
    :].
    -0.25
     dedicate
    -0.25
    ...@
    -0.24
    ']:
    -0.24
    )：
    -0.23
    贅沢
    -0.23
     regulating
    -0.23
    POSITIVE LOGITS
    AddHtmlAttribute
    0.83
     betweenstory
    0.73
     AssemblyTitle
    0.73
     समीक्षाओं
    0.66
     HttpNotFound
    0.66
     Autorisations
    0.63
    IntoConstraints
    0.62
    باردا
    0.62
    曖昧さ回避
    0.62
    yntaxException
    0.61
    Activations Density 0.725%

    No Known Activations