© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3266
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs related to hardware or low-level system interactions

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

    Code snippets related to hardware or cloud services

    np_acts-logits-general · gemini-2.0-flash

    bus() argument

    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
    StoryboardSegue
    -0.62
     ExecuteAsync
    -0.60
     oprot
    -0.55
     Lightboxes
    -0.52
     CURIAM
    -0.50
    ContentAsync
    -0.50
     للمعارف
    -0.50
    UnusedPrivate
    -0.49
     snippetHide
    -0.48
    featureID
    -0.47
    POSITIVE LOGITS
    RegistryLite
    0.40
    MeasureSpec
    0.37
    AnimationsModule
    0.36
     appris
    0.36
    Купить
    0.36
     maravillas
    0.35
    hkan
    0.35
    okości
    0.35
     fueled
    0.35
     geschiedenis
    0.34
    Activations Density 0.367%

    No Known Activations