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. 14384
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical conditions and their implications

    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
     autorytatywna
    -0.87
    numerusform
    -0.78
     ویکی‌پدیا
    -0.73
     Numerade
    -0.73
    Hentet
    -0.72
     beginnetje
    -0.72
    Hauptartikel
    -0.71
     fubject
    -0.71
     ModelExpression
    -0.71
     theſe
    -0.70
    POSITIVE LOGITS
    󠁢
    0.81
    //
    0.61
    TagHelper
    0.60
     GenerationType
    0.56
    
    0.55
    sproz
    0.53
    ghijklmnop
    0.53
    aimana
    0.51
    CompilerServices
    0.51
     G
    0.51
    Activations Density 0.480%

    No Known Activations