© 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. 3795
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or organizational entities and technical specifications

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

    Abbreviations after an open parenthesis

    np_acts-logits-general · gemini-2.0-flash

    Australian abbreviations and acronyms

    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
     tramonto
    -0.68
    IntoConstraints
    -0.67
     bicchiere
    -0.62
     paesaggio
    -0.59
    antMatchers
    -0.58
     giudizio
    -0.58
     pescoço
    -0.58
     Virgil
    -0.57
     Spart
    -0.57
    tableFuture
    -0.56
    POSITIVE LOGITS
    uno
    0.93
    lio
    0.92
    rio
    0.89
    leo
    0.89
     Waldo
    0.88
    ingo
    0.86
    yo
    0.85
    tio
    0.85
    ilo
    0.83
    ido
    0.83
    Activations Density 0.707%

    No Known Activations