© 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. 82013
    Prev
    Next
    INDEX
    Explanations

    references to user interface elements in code, specifically related to table views and text fields

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

    UITextFields UITableView Parkinson

    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
     queſta
    -0.81
    ſelf
    -0.72
     newOwner
    -0.70
     surla
    -0.64
    esModule
    -0.64
    FunctionFlags
    -0.63
     HasFactory
    -0.63
     otomatig
    -0.62
    CppCodeGen
    -0.60
    enderror
    -0.59
    POSITIVE LOGITS
     tableView
    0.95
     collectionView
    0.55
    tableView
    0.54
    TableView
    0.37
     sampling
    0.37
    buttonShape
    0.36
    ScopeManager
    0.34
    findpost
    0.34
     Table
    0.33
     onItemClick
    0.33
    Activations Density 0.001%

    No Known Activations