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. 20-GEMMASCOPE-RES-16K
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    events related to trades or transactions in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microbiome
    -1.07
     selfies
    -0.94
     selfie
    -0.92
     CrossFit
    -0.91
     STEM
    -0.91
     YouTuber
    -0.89
     GoFundMe
    -0.88
     онлайн
    -0.87
     Brexit
    -0.86
     qPCR
    -0.86
    POSITIVE LOGITS
     daß
    0.92
     Soviet
    0.86
     USSR
    0.83
     postwar
    0.75
     Yugoslavia
    0.72
     müßte
    0.71
     Czechoslovakia
    0.71
     Rhodesia
    0.71
     läßt
    0.70
     jugos
    0.70
    Activations Density 2.865%

    No Known Activations