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. 14390
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to health and medical conditions

    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
    ்கள்
    -0.78
    ്
    -0.73
    gulp
    -0.70
     sy
    -0.68
     स्
    -0.68
    เ
    -0.68
     jakie
    -0.67
     permanentes
    -0.67
     بودم
    -0.67
    égek
    -0.67
    POSITIVE LOGITS
     itſelf
    1.33
     ſind
    1.21
     myſelf
    1.14
     Efq
    1.13
    BibitemShut
    1.11
     iſt
    1.11
    theless
    1.05
     ―――――
    1.03
     becauſe
    1.01
     ་་
    1.01
    Activations Density 0.589%

    No Known Activations