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. 5-GEMMASCOPE-RES-16K
    6. 9938
    Prev
    Next
    INDEX
    Explanations

    terms related to sealing or seals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sted
    -0.70
     Daryl
    -0.66
     Wey
    -0.62
     Miley
    -0.60
     Moreno
    -0.60
     χρη
    -0.59
     Kuru
    -0.59
     Vorte
    -0.58
     Dwight
    -0.57
    ể
    -0.57
    POSITIVE LOGITS
     seal
    2.20
     seals
    2.07
     Seal
    1.96
    seal
    1.85
     Seals
    1.85
     stamp
    1.81
    Seal
    1.80
     Sealing
    1.79
     sealing
    1.78
     Stamp
    1.70
    Activations Density 0.067%

    No Known Activations