© 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. 7153
    Prev
    Next
    INDEX
    Explanations

    references to repository interfaces and classes used in programming contexts

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

    Code repositories and related terms

    np_acts-logits-general · gemini-2.0-flash

    repository or repo

    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
    Law
    -0.52
    CharCode
    -0.50
     Irán
    -0.48
    Süd
    -0.47
    wrong
    -0.46
    følgelig
    -0.46
     Kerja
    -0.46
     vœ
    -0.45
     ſon
    -0.45
    Jim
    -0.45
    POSITIVE LOGITS
     repository
    1.12
    Repository
    1.09
     Repository
    1.06
    repository
    0.96
     repositories
    0.92
    getRepository
    0.89
    UserRepository
    0.88
    Repositories
    0.86
    repositories
    0.84
     UserRepository
    0.83
    Activations Density 0.157%

    No Known Activations