© 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. 31-GEMMASCOPE-RES-16K
    11. 3291
    Prev
    Next
    INDEX
    Explanations

    keywords and constructs related to programming and asynchronous functions

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

    asynchronous programming patterns and promise/future handling in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RegressionTest
    -0.76
    DockStyle
    -0.69
    UnusedPrivate
    -0.66
     AppCompatTheme
    -0.62
    majánló
    -0.62
    migrationBuilder
    -0.62
    DebuggerNonUser
    -0.61
     Wiktionnaire
    -0.61
    WebServlet
    -0.60
    脚注の使い方
    -0.60
    POSITIVE LOGITS
    Promise
    0.49
     Promise
    0.47
     promise
    0.46
    Done
    0.46
    Future
    0.43
     future
    0.42
     completion
    0.41
     Done
    0.41
    promise
    0.41
     Future
    0.40
    Activations Density 0.379%

    No Known Activations