© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    occurrences of Japanese characters or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    everybody listen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poichè
    -0.88
     pò
    -0.83
     appunto
    -0.77
     میتوان
    -0.77
    ichè
    -0.74
    :✨
    -0.72
     perchè
    -0.71
    writeFieldEnd
    -0.71
     IIRC
    -0.69
     gdyż
    -0.69
    POSITIVE LOGITS
     everybody
    0.60
      (
    0.55
    Everybody
    0.53
     anybody
    0.50
     Everybody
    0.49
     listen
    0.48
    yntaxException
    0.48
    everybody
    0.47
     coti
    0.46
    Unload
    0.46
    Activations Density 0.100%

    No Known Activations