© 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. 13385
    Prev
    Next
    INDEX
    Explanations

    structures and formatting elements in documents, particularly related to data representations and mathematical notations

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

    Characters followed by brackets

    np_acts-logits-general · gemini-2.0-flash

    bracket sequences

    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
     Hakim
    -0.65
    Ach
    -0.56
     Willy
    -0.55
    hermes
    -0.54
     Rasa
    -0.52
    Aya
    -0.52
     Ches
    -0.52
    Willy
    -0.52
     Pacer
    -0.51
     Dune
    -0.51
    POSITIVE LOGITS
     '[
    1.13
    ("[
    1.09
    "[
    1.02
    ('[
    1.02
     "[
    1.01
    '[
    1.01
    [[
    0.99
    :[
    0.98
    /[
    0.98
    .[
    0.97
    Activations Density 1.548%

    No Known Activations