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. 13-GEMMASCOPE-RES-16K
    6. 12729
    Prev
    Next
    INDEX
    Explanations

    references to different types of bags, especially in a context involving size or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.98
     onCancelled
    -0.90
    ']],
    -0.88
     disponibilités
    -0.88
     CommonModule
    -0.88
    ">:
    -0.85
     EPIC
    -0.85
    Viki
    -0.85
    "]));
    -0.85
    хьтан
    -0.84
    POSITIVE LOGITS
     bags
    1.94
     bag
    1.90
    bag
    1.88
     Bag
    1.75
    bags
    1.74
    Bag
    1.72
     BAG
    1.64
     Bags
    1.61
    BAG
    1.58
    Bags
    1.39
    Activations Density 0.104%

    No Known Activations