© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6447
    Prev
    Next
    INDEX
    Explanations

    syntactical structures related to conditional statements and function calls in programming

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

    Code: parentheses, brackets, and curly braces

    np_acts-logits-general · gemini-2.0-flash

    statement endings after conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.78
    Descripció
    -0.76
    writeFieldEnd
    -0.73
    ItemBackground
    -0.69
    WindowConstants
    -0.69
     Baillargeon
    -0.69
    principalTable
    -0.67
    contentLoaded
    -0.60
     kaarangay
    -0.59
    发表于
    -0.58
    POSITIVE LOGITS
     {
    0.78
     {
    0.71
    </h3>
    0.57
    '){
    0.54
    }*/
    0.53
    0.52
    "){

    0.50
    endphp
    0.50
    Identification
    0.50
     }}</
    0.50
    Activations Density 0.048%
    No Known Activations