© 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. 3006
    Prev
    Next
    INDEX
    Explanations

    references to the React framework and related React libraries

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

    "React" (JavaScript library) and reactions

    np_acts-logits-general · gemini-2.0-flash

    response/reaction to events

    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
    ishment
    -0.48
     kasarigan
    -0.48
    omba
    -0.47
     cim
    -0.46
    SystemColors
    -0.46
    
    -0.46
     dispen
    -0.45
    ‍♂️
    -0.45
    mby
    -0.45
     Omb
    -0.45
    POSITIVE LOGITS
    react
    1.24
     React
    1.21
    React
    1.14
     react
    1.02
     REACT
    0.98
     réactions
    0.98
    REACT
    0.97
    reaction
    0.95
     réaction
    0.94
     reação
    0.94
    Activations Density 0.133%

    No Known Activations