© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 1925
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and structures, particularly related to function definitions and asynchronous operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.69
    PyExc
    -0.55
    ftagPool
    -0.55
     defaultstate
    -0.54
     AssemblyTitle
    -0.52
     AssemblyVersion
    -0.49
     @"/
    -0.47
     "..\..\..\
    -0.47
    TypedDataSet
    -0.46
    CloseOperation
    -0.46
    POSITIVE LOGITS
    const
    1.45
    console
    1.29
     const
    1.24
    let
    1.19
     console
    1.16
     let
    1.09
    setTimeout
    0.73
     Const
    0.71
     consoles
    0.69
    var
    0.67
    Activations Density 0.145%

    No Known Activations