© 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. 14762
    Prev
    Next
    INDEX
    Explanations

    various types of conditional and looping statements in programming code

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

    Code syntax: parentheses and brackets

    np_acts-logits-general · gemini-2.0-flash

    exception handling and code structure

    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
    ){
    -0.81
     ){
    -0.81
    ?
    -0.80
    (){
    -0.76
     }{
    -0.75
    </td>
    -0.74
    <h4>
    -0.73
    </h5>
    -0.67
     */
    -0.66
     (){
    -0.66
    POSITIVE LOGITS
    ”).
    0.66
    "):
    0.65
    '):
    0.64
    "])
    0.64
    ’).
    0.62
    >");
    0.61
    vrons
    0.61
    ⟬
    0.61
    ocities
    0.59
    archiviato
    0.59
    Activations Density 0.025%

    No Known Activations