© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9817
    Prev
    Next
    INDEX
    Explanations

    syntax related to programming constructs and events in code

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

    Code or game development loops/updates

    np_acts-logits-general · gemini-2.0-flash

    game loop updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebControls
    -0.59
     esist
    -0.50
     stimmen
    -0.48
    Spoljašnje
    -0.44
    WebElementEntity
    -0.44
    ThroughAttribute
    -0.44
    wness
    -0.44
    Thrown
    -0.42
     EXIST
    -0.42
    cshtml
    -0.41
    POSITIVE LOGITS
     Update
    1.05
     update
    1.04
     FixedUpdate
    0.91
     updates
    0.91
     Updates
    0.90
     tick
    0.87
    posedge
    0.86
    Update
    0.86
    update
    0.86
    deltaTime
    0.82
    Activations Density 0.217%

    No Known Activations