© 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. 15030
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating the timing of events

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

    "Shortly" followed by "after" or "before"

    np_acts-logits-general · gemini-2.0-flash

    shortly before or after

    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
     AssemblyTitle
    -0.73
    enderror
    -0.70
     الاطلاع
    -0.69
     AssemblyCulture
    -0.68
    клопе
    -0.67
    NameInMap
    -0.66
     JpaRepository
    -0.64
     BrowserModule
    -0.63
    Collegamenti
    -0.62
    "):
    -0.59
    POSITIVE LOGITS
     after
    1.87
     before
    1.80
    after
    1.50
    before
    1.48
     antes
    1.30
     AFTER
    1.27
     afterwards
    1.24
     BEFORE
    1.23
     afterward
    1.22
    AFTER
    1.21
    Activations Density 0.179%

    No Known Activations