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. 3-GEMMASCOPE-RES-16K
    6. 16220
    Prev
    Next
    INDEX
    Explanations

    references to spas and wellness-related services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.80
    IUrlHelper
    -0.77
     honte
    -0.75
     transférez
    -0.71
     Grüsse
    -0.71
     Wikimedijinoj
    -0.68
    DoubleQuotes
    -0.66
     مشين
    -0.66
     vej
    -0.65
     Connectez
    -0.64
    POSITIVE LOGITS
     Spa
    2.96
     spa
    2.94
    Spa
    2.69
    spa
    2.35
     SPA
    2.24
     spas
    1.99
     Spas
    1.76
    SPA
    1.72
    Спа
    1.11
     massage
    1.09
    Activations Density 0.070%

    No Known Activations