© 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. 14571
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function signatures and parameter lists

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

    Code with commas followed by a data type

    np_acts-logits-general · gemini-2.0-flash

    code, APIs, and state

    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
    almost
    -0.35
     przecież
    -0.35
     almost
    -0.34
    Enllaces
    -0.29
     Hälfte
    -0.29
     majd
    -0.29
     Tatsache
    -0.28
     infatti
    -0.28
     Almost
    -0.28
     Mitglieder
    -0.28
    POSITIVE LOGITS
    脚注の使い方
    0.69
    BibitemShut
    0.65
     EconPapers
    0.63
     שוליים
    0.63
     diocese
    0.62
    vinfos
    0.61
    Зноскі
    0.60
     ſind
    0.59
    tershire
    0.59
    Zulu
    0.58
    Activations Density 0.203%

    No Known Activations