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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1633
    Prev
    Next
    INDEX
    Explanations

    function and method declaration and closing syntax in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     looks
    -0.60
     Hines
    -0.59
     trans
    -0.59
    catel
    -0.57
     nama
    -0.56
    ÍTULO
    -0.56
     Schwab
    -0.55
    Externí
    -0.55
    plate
    -0.54
    OnItem
    -0.54
    POSITIVE LOGITS
    ){
    2.75
    "){
    2.54
    '){
    2.51
    ]){
    2.45
    )){
    2.45
    ++){
    2.39
    ")){
    2.34
    ']){
    2.34
    ))){
    2.34
    "])){
    2.32
    Activations Density 0.163%

    No Known Activations