© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 14680
    Prev
    Next
    INDEX
    Explanations

    event lifecycle methods in programming, specifically related to component mounting or loading

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

    lifecycle or initialization methods

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    fano
    -0.51
     sche
    -0.50
    __::
    -0.47
    putable
    -0.44
    发表于
    -0.43
    atilde
    -0.43
    PositiveButton
    -0.43
    ":[{
    -0.43
    )')
    -0.42
    AddWithValue
    -0.42
    POSITIVE LOGITS
     viewDidLoad
    0.71
     OnInit
    0.71
     initState
    0.66
    Unmount
    0.63
     useEffect
    0.60
    useEffect
    0.59
    IContainer
    0.59
    Mount
    0.57
     فريبيس
    0.56
    PreExecute
    0.56
    Activations Density 0.001%

    No Known Activations