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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11301
    Prev
    Next
    INDEX
    Explanations

    technical terms and coding constructs related to graphical rendering and shading

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

    Code snippets or shader code

    np_acts-logits-general · gemini-2.0-flash

    graphics programming and geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cemment
    -0.43
    opardy
    -0.32
     Gauge
    -0.31
    дый
    -0.30
    entraî
    -0.30
    méno
    -0.29
    gauge
    -0.29
    Typing
    -0.29
    eclipse
    -0.28
     CanadaChoose
    -0.28
    POSITIVE LOGITS
    Aholisi
    0.68
     BoxFit
    0.65
    PostInfinity
    0.64
    outWeight
    0.63
    InjectAttribute
    0.62
     AssemblyProduct
    0.62
    ViewImports
    0.61
    tangentMode
    0.61
     esternos
    0.61
    Xna
    0.60
    Activations Density 0.330%

    No Known Activations