© 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. 790
    Prev
    Next
    INDEX
    Explanations

    mentions of repositories, specifically in the context of code or data management

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

    software development terms related to repositories and code management.

    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
     informée
    -0.49
     שוליים
    -0.48
    Хьажоргаш
    -0.48
    Autowired
    -0.47
    Wis
    -0.47
    Cosmic
    -0.47
    Billie
    -0.47
    scalatest
    -0.46
    Süd
    -0.46
    Stark
    -0.45
    POSITIVE LOGITS
     repository
    1.05
     Repository
    1.02
    Repository
    1.02
    getRepository
    0.91
    repository
    0.89
    UserRepository
    0.85
     repositories
    0.80
    Repositories
    0.79
     Repo
    0.79
    pository
    0.77
    Activations Density 0.077%

    No Known Activations