© 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. 1421
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Well" used to introduce or transition statements

    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
    TagMode
    -0.69
     TextAppearance
    -0.64
    cionario
    -0.61
    newArrayList
    -0.54
    */),
    -0.53
    }}^{(
    -0.51
     stammen
    -0.51
     industrielle
    -0.50
     industriale
    -0.49
    cody
    -0.48
    POSITIVE LOGITS
     maybe
    0.91
     technically
    0.79
     firstly
    0.79
     then
    0.76
     actually
    0.73
     hopefully
    0.73
     luckily
    0.73
     duh
    0.73
     okay
    0.73
     obviously
    0.72
    Activations Density 0.024%

    No Known Activations