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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6449
    Prev
    Next
    INDEX
    Explanations

    quantities or references to numbers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.00
     Jefus
    -0.99
    ſelf
    -0.94
     Efq
    -0.93
     Houſe
    -0.92
     myſelf
    -0.88
     himſelf
    -0.88
     Phry
    -0.87
     alps
    -0.86
     photolibrary
    -0.82
    POSITIVE LOGITS
     three
    2.46
     four
    2.18
     five
    2.05
     two
    2.05
     six
    1.87
    three
    1.85
     trois
    1.82
     quatre
    1.73
     seven
    1.71
     eight
    1.69
    Activations Density 0.196%

    No Known Activations