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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2798
    Prev
    Next
    INDEX
    Explanations

    references to food and culinary experiences, particularly those highlighting local, organic, or sustainable ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.74
    idorm
    -0.60
    LookAnd
    -0.59
    RenderAtEndOf
    -0.57
    DeleteBehavior
    -0.54
    ernalia
    -0.52
     Chriftian
    -0.51
     Inadequate
    -0.50
    atorship
    -0.50
    tagHelperRunner
    -0.49
    POSITIVE LOGITS
     organic
    1.24
     organically
    1.17
     natural
    1.16
     sustainably
    1.05
     handmade
    1.04
     Organic
    1.01
    organic
    1.01
     artisanal
    1.01
     handcrafted
    1.00
     artisan
    0.99
    Activations Density 0.186%

    No Known Activations