© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 89544
    Prev
    Next
    INDEX
    Explanations

    conjunctions and other phrases that indicate legal conditions or sequences

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

    IT IS FURTHER ORDERED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Houſe
    -0.67
     pinulongan
    -0.67
     Efq
    -0.66
     useAppContext
    -0.59
    reportWebVitals
    -0.59
     ISNI
    -0.58
     ſmall
    -0.58
     незавершена
    -0.57
    Diweddarwch
    -0.57
     Theſe
    -0.57
    POSITIVE LOGITS
     amaç
    0.39
     παρά
    0.38
     circonstances
    0.35
    目的
    0.35
    präsident
    0.35
     przygoto
    0.34
     подготов
    0.34
     …
    0.33
     czer
    0.32
    lehnt
    0.32
    Activations Density 0.057%

    No Known Activations