© 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. 12109
    Prev
    Next
    INDEX
    Explanations

    data structure paths and references in code

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

    File paths or URLs

    np_acts-logits-general · gemini-2.0-flash

    file paths and urls

    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
     Chapin
    -0.66
     Lockhart
    -0.66
     Muir
    -0.64
     AES
    -0.58
     Hendrix
    -0.57
     Clare
    -0.56
    chai
    -0.55
     ła
    -0.55
     Czar
    -0.54
    ThroughAttribute
    -0.54
    POSITIVE LOGITS
     "/
    1.17
    )/
    1.13
     '/
    1.12
    ]/
    1.12
    ="/
    1.12
    "/
    1.09
    ("/
    1.06
    }/
    1.06
    '/
    1.05
    :'/
    1.05
    Activations Density 0.470%

    No Known Activations