© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1631
    Prev
    Next
    INDEX
    Explanations

    capitalized words at the beginning of sentences or phrases, particularly when they start with "T" or are part of an alphabetical or ordered list.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    references to specific characters, letters, or items within written content

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

    Non-English alphabet letters or symbols

    np_acts-logits-general · gemini-2.0-flash

    sequences of letters and symbols

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     lenker
    -0.49
     gynhyrchwyd
    -0.47
    UpInside
    -0.45
    haustible
    -0.45
     utafitiHapana
    -0.44
    swire
    -0.43
     aapt
    -0.42
     gedaan
    -0.41
     toegang
    -0.41
    tiple
    -0.40
    POSITIVE LOGITS
     '\\;'
    0.73
    XmlAccessType
    0.42
    جغرافيا
    0.42
    
    0.42
     lettera
    0.39
    alphabet
    0.38
     mandatario
    0.37
     referenties
    0.36
    なぜ
    0.36
    abcdefghijklmnop
    0.35
    Activations Density 0.686%

    No Known Activations