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-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6779
    Prev
    Next
    INDEX
    Explanations

    items related to crafting, specifically those that involve paper and embellishments

    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
    IsContent
    -0.60
     salade
    -0.54
     moletom
    -0.51
     säll
    -0.50
    colgroup
    -0.49
     planches
    -0.47
    zież
    -0.47
    AxisSize
    -0.45
    ած
    -0.45
     lengte
    -0.45
    POSITIVE LOGITS
     embell
    0.92
     gold
    0.91
     accents
    0.83
     details
    0.82
     detail
    0.81
     decorations
    0.78
     rhinestone
    0.75
     detailing
    0.74
    gold
    0.73
     decoration
    0.73
    Activations Density 0.123%

    No Known Activations