© 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. 22-GEMMASCOPE-RES-16K
    11. 12328
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts or theories related to groups and combinatorial structures

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

    Mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.0-flash

    les applications, la condición

    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
     Bayard
    -0.56
     scoops
    -0.55
    impre
    -0.53
     proofs
    -0.52
     rehabilitation
    -0.52
     impatiently
    -0.51
     infrastructures
    -0.51
     toppers
    -0.51
     beh
    -0.50
     penit
    -0.50
    POSITIVE LOGITS
     ${\
    0.86
    ${\
    0.69
     ($
    0.64
    setVerticalGroup
    0.62
     numerus
    0.59
     culturelles
    0.58
    expandindo
    0.56
     ${
    0.56
     ModelExpression
    0.55
     vœux
    0.55
    Activations Density 0.174%

    No Known Activations