© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16182
    Prev
    Next
    INDEX
    Explanations

    instances of specific structured document or programming format indicators

    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
     gestern
    -0.76
     yesterday
    -0.73
     Yesterday
    -0.70
    最近の
    -0.69
    Yesterday
    -0.68
     tomorrow
    -0.68
     récente
    -0.68
    今回も
    -0.67
    今後も
    -0.65
    yesterday
    -0.64
    POSITIVE LOGITS
     initially
    0.93
     began
    0.89
     Initially
    0.86
     inicialmente
    0.83
    Initially
    0.82
     Тогда
    0.79
    偶然
    0.77
     then
    0.77
     awalnya
    0.76
     intrigued
    0.75
    Activations Density 0.410%

    No Known Activations