© 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. 41-GEMMASCOPE-RES-16K
    11. 13068
    Prev
    Next
    INDEX
    Explanations

    programming constructs and structures relevant to C++ syntax and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arraycopy
    -0.57
    OPSIS
    -0.41
    rungsseite
    -0.41
     null
    -0.37
    boolean
    -0.36
     Daß
    -0.36
    TagMode
    -0.35
     AssemblyCulture
    -0.34
    nowrap
    -0.34
    folger
    -0.33
    POSITIVE LOGITS
    std
    1.63
     std
    1.63
    auto
    1.07
     nullptr
    1.06
    nullptr
    1.00
     constexpr
    0.97
    constexpr
    0.94
     auto
    0.91
    boost
    0.79
     [](
    0.79
    Activations Density 0.397%

    No Known Activations