© 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. 20-GEMMASCOPE-RES-16K
    11. 16198
    Prev
    Next
    INDEX
    Explanations

    technical terminology and frameworks related to research or academic contexts

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

    ending in "-ary", "-arily", or "-tion"

    np_acts-logits-general · gemini-2.0-flash

    -ary and -arily suffixes

    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
     calendriers
    -0.72
    WebElementEntity
    -0.53
     annuelle
    -0.53
     électroniques
    -0.53
    pośred
    -0.52
    usias
    -0.52
    NewLabel
    -0.52
    żli
    -0.51
    userManager
    -0.51
     CallOverrides
    -0.51
    POSITIVE LOGITS
    ary
    1.49
    ARY
    1.28
    aries
    1.24
     ary
    1.17
    arily
    1.16
    ery
    1.07
    airy
    1.00
    arv
    0.95
    lary
    0.93
    ario
    0.90
    Activations Density 0.243%

    No Known Activations