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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12767
    Prev
    Next
    INDEX
    Explanations

    elements related to growth and development in various contexts

    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-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
    μβρίου
    -0.37
    等
    -0.32
     swoim
    -0.31
    DET
    -0.30
    Carriera
    -0.29
    Resource
    -0.29
    odziel
    -0.29
    呢
    -0.28
     odst
    -0.28
    September
    -0.27
    POSITIVE LOGITS
    onViewCreated
    0.88
     Мексичка
    0.72
     ویکی‌پدی
    0.71
     estekak
    0.70
    nextProps
    0.68
     ***!
    0.67
     deſſen
    0.66
    interopRequire
    0.66
     Menſchen
    0.65
    abstractmethod
    0.65
    Activations Density 1.372%

    No Known Activations