© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4215
    Prev
    Next
    INDEX
    Explanations

    conversational transitions or informal markers

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

    internet/text communication fillers like "by the way" (BTW), conversation markers, and casual interjections.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     vPvB
    -0.38
     nią
    -0.37
     ogran
    -0.37
     limitado
    -0.35
    badlogic
    -0.35
    setCellValue
    -0.34
     situações
    -0.34
     necessárias
    -0.34
     naselje
    -0.34
     behov
    -0.33
    POSITIVE LOGITS
     incidentally
    0.90
     Incidentally
    0.85
     btw
    0.83
    brigens
    0.82
    GEBURTSDATUM
    0.80
    Кстати
    0.75
     übrigens
    0.75
     BTW
    0.74
    Btw
    0.71
    BTW
    0.68
    Activations Density 0.119%

    No Known Activations