© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14781
    Prev
    Next
    INDEX
    Explanations

    terms and definitions associated with names and their meanings

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

    and phrases that signify definition or explanation

    np_acts-logits-general · gemini-2.0-flash

    explaining word meanings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FTFY
    -0.77
     <>",
    -0.66
     hindurch
    -0.65
    hijab
    -0.65
    uttavia
    -0.62
     xenia
    -0.61
    tdessen
    -0.60
    grunge
    -0.59
    }:${
    -0.59
    IContainer
    -0.58
    POSITIVE LOGITS
     literally
    0.87
    literally
    0.82
     literalmente
    0.78
     Literally
    0.73
     meaning
    0.70
     буквально
    0.70
     litté
    0.68
    ficie
    0.67
    的意思
    0.66
    translates
    0.64
    Activations Density 0.190%

    No Known Activations