© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 14689
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in a programming context

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

    Labels in GUI code or HTML

    np_acts-logits-general · gemini-2.0-flash

    GUI labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    χρι
    -0.59
     виправивши
    -0.58
    Eksterne
    -0.57
    PostExecute
    -0.56
     schop
    -0.53
     Wicidata
    -0.53
    sweise
    -0.53
    навли
    -0.48
    wiście
    -0.47
    öglich
    -0.47
    POSITIVE LOGITS
     jLabel
    0.90
    QLabel
    0.89
    jLabel
    0.87
     JLabel
    0.86
     QLabel
    0.85
    AutoSize
    0.84
    JLabel
    0.79
    labelledby
    0.69
     label
    0.68
    PerformLayout
    0.68
    Activations Density 0.019%

    No Known Activations