© 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
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5661
    Prev
    Next
    INDEX
    Explanations

    keywords associated with programming logic and structures, particularly relating to events and elements in a structured code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.94
    parsedMessage
    -0.90
    RectangleBorder
    -0.75
    iſchen
    -0.74
    MLLoader
    -0.74
    rrggbb
    -0.73
     vooz
    -0.73
    Tikang
    -0.73
    <pad>
    -0.71
    <unused16>
    -0.71
    POSITIVE LOGITS
     {
    0.88
     {
    
    0.82
    ){
    0.77
    (){
    0.73
    )
    0.72
     ){
    0.70
    "){
    0.63
    '){
    0.62
    ){
    
    0.56
    ”
    0.54
    Activations Density 0.446%

    No Known Activations