© 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. 8048
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitional phrases that indicate connections in reasoning or opposing ideas

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

    Sentences ending with a period

    np_acts-logits-general · gemini-2.0-flash

    connecting sentence beginnings

    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
    orneys
    -0.63
    wußt
    -0.62
     SafeMath
    -0.61
    Шаг
    -0.60
    softc
    -0.58
    taminophen
    -0.57
     Audubon
    -0.56
    AddAttribute
    -0.56
    \|^{
    -0.56
    fhir
    -0.55
    POSITIVE LOGITS
    Moreover
    1.21
    Nowadays
    1.20
     Nowadays
    1.19
     Moreover
    1.18
    Apart
    1.14
     Apart
    1.12
     Besides
    1.09
    Besides
    1.05
    Furthermore
    1.02
     Nevertheless
    1.01
    Activations Density 0.760%

    No Known Activations