© 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. 21-GEMMASCOPE-RES-16K
    11. 16069
    Prev
    Next
    INDEX
    Explanations

    references to optimal strategies and estimation in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.54
    saraba
    -0.51
    Carriera
    -0.48
     Mer
    -0.44
    
    -0.44
    CodeAttribute
    -0.43
     slo
    -0.42
    ంట
    -0.42
    [:-
    -0.41
     ste
    -0.41
    POSITIVE LOGITS
     minimum
    1.77
     maximization
    1.69
     maximum
    1.68
     maximizing
    1.68
     minimization
    1.67
     maximize
    1.64
     minim
    1.63
     maximized
    1.60
     Minimum
    1.60
     max
    1.58
    Activations Density 0.919%

    No Known Activations