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. 9163
    Prev
    Next
    INDEX
    Explanations

    references to online shopping and the liquors market

    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
     myſelf
    -0.91
     Moslem
    -0.83
     themſelves
    -0.81
     himſelf
    -0.81
     Jefus
    -0.79
     gouver
    -0.79
     uſe
    -0.78
     purpoſe
    -0.77
     Mahomet
    -0.75
     ſeveral
    -0.74
    POSITIVE LOGITS
     upto
    1.02
     irrespective
    1.00
     atleast
    0.96
    upto
    0.90
     fundas
    0.89
    contd
    0.87
     hence
    0.87
     erst
    0.84
    Contd
    0.82
     till
    0.82
    Activations Density 1.105%

    No Known Activations