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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2287
    Prev
    Next
    INDEX
    Explanations

    elements related to culinary competitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.56
    طنين
    -0.50
    useNewUrlParser
    -0.49
     regular
    -0.45
    文庫
    -0.45
     die
    -0.45
     купить
    -0.43
     contract
    -0.43
    ciclop
    -0.42
    zaken
    -0.42
    POSITIVE LOGITS
     creativity
    0.94
     submissions
    0.93
     Creativity
    0.86
     submission
    0.83
     creative
    0.81
     creations
    0.81
     submitted
    0.80
    writeField
    0.77
    Creativity
    0.77
     creatively
    0.75
    Activations Density 0.216%

    No Known Activations