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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9522
    Prev
    Next
    INDEX
    Explanations

    references to significant political events or legislative actions

    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
     CreateTagHelper
    -0.92
    PerformLayout
    -0.87
    InjectAttribute
    -0.75
     MessageBoxIcon
    -0.70
     Normdatei
    -0.70
    Diweddarwch
    -0.69
    Personendaten
    -0.68
    MLLoader
    -0.65
    jspx
    -0.65
    iented
    -0.64
    POSITIVE LOGITS
     Brexit
    1.14
    Brexit
    0.95
     EU
    0.89
    EU
    0.77
     BRE
    0.68
     post
    0.64
     bre
    0.63
     Britain
    0.63
     exit
    0.62
     Bre
    0.61
    Activations Density 0.055%

    No Known Activations