Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 67583
    Prev
    Next
    INDEX
    Explanations

    terms related to epigenetic factors and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     contextLoads
    -0.59
     JpaRepository
    -0.53
    pannt
    -0.52
    ollectionView
    -0.51
    centralwidget
    -0.49
     }{@
    -0.49
    onViewCreated
    -0.49
     Hons
    -0.49
    PDOException
    -0.48
     саны
    -0.48
    POSITIVE LOGITS
     epigenetic
    0.63
     methylation
    0.53
     fenómenos
    0.40
    ագրություններ
    0.39
     huella
    0.37
    tierung
    0.37
     inversiones
    0.36
     unido
    0.36
     erasure
    0.35
     sellado
    0.35
    Activations Density 0.067%

    No Known Activations