© 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. 0-GEMMASCOPE-RES-16K
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    indented lines or sections that appear structured, indicating a specific format or pattern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */
    -0.56
    publique
    -0.55
     regards
    -0.54
    britanni
    -0.53
     piace
    -0.52
     onAnimation
    -0.51
    {
    -0.51
    Tembelea
    -0.51
     Intent
    -0.51
    CloseOperation
    -0.50
    POSITIVE LOGITS
     CURIAM
    0.75
                     
    0.64
                       
    0.63
    Демографія
    0.62
    0.62
    GEBURTSDATUM
    0.62
    ration
    0.60
                         
    0.60
                  
    0.59
                      
    0.59
    Activations Density 1.033%

    No Known Activations