© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11483
    Prev
    Next
    INDEX
    Explanations

    calls to superclass methods in object-oriented programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []){
    -0.61
    glom
    -0.54
    ")){
    
    -0.52
    "+
    
    -0.52
     GLFW
    -0.51
    MutableLiveData
    -0.50
    PushMatrix
    -0.50
    "){
    
    -0.50
    AddTagHelper
    -0.49
    '){
    
    -0.48
    POSITIVE LOGITS
    super
    0.78
     super
    0.77
     súper
    0.64
    writeFieldEnd
    0.64
    reportWebVitals
    0.64
    orescence
    0.64
     супер
    0.63
    حياتها
    0.61
    Билгалдахарш
    0.61
    styleUrls
    0.60
    Activations Density 0.019%

    No Known Activations