© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 48193
    Prev
    Next
    INDEX
    Explanations

    methods related to focus and blur events in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    TypedDataSet
    -0.60
     snippetHide
    -0.51
    fastjson
    -0.50
     endforeach
    -0.50
    onOptions
    -0.50
    findpost
    -0.49
     ExecuteAsync
    -0.49
    SizeMode
    -0.48
    LookAnd
    -0.48
    BitmapFactory
    -0.47
    POSITIVE LOGITS
    onBlur
    0.68
    onFocus
    0.49
    Blur
    0.48
     touche
    0.46
    blur
    0.45
     InputDecoration
    0.44
    ArrowToggle
    0.42
    posedge
    0.42
     Numerade
    0.42
     layout
    0.41
    Activations Density 0.004%

    No Known Activations