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. 11298
    Prev
    Next
    INDEX
    Explanations

    references to legal divisions or sections within legal texts

    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
     resourceCulture
    -0.96
    lccn
    -0.86
    Laos
    -0.71
     Carthag
    -0.70
     Phuket
    -0.69
     Agamemnon
    -0.68
    ínű
    -0.68
     Nazareth
    -0.67
     Alha
    -0.66
    Hein
    -0.65
    POSITIVE LOGITS
     division
    2.15
     divisions
    1.98
     Division
    1.89
     DIVISION
    1.80
    division
    1.80
     Divisions
    1.80
    Division
    1.80
     divis
    1.75
    DIVISION
    1.69
     divide
    1.68
    Activations Density 0.071%

    No Known Activations