© 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. 2-GEMMASCOPE-RES-16K
    11. 4086
    Prev
    Next
    INDEX
    Explanations

    elements of structured data representation, particularly in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yargs
    -0.80
    itinéraire
    -0.77
    nestjs
    -0.69
    AntiForgeryToken
    -0.68
    putInt
    -0.67
    RefNanny
    -0.67
     DeWitt
    -0.67
     Hoyt
    -0.65
    ensity
    -0.63
    cri
    -0.63
    POSITIVE LOGITS
                  
    1.12
                   
    0.83
     censiti
    0.77
    twimg
    0.70
    er
    0.66
     Fenton
    0.65
    CodeAttribute
    0.65
    されました
    0.64
     Falcons
    0.62
     Presto
    0.61
    Activations Density 0.117%

    No Known Activations