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. 14394
    Prev
    Next
    INDEX
    Explanations

    references to Western culture or geographical regions

    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
    iseite
    -0.75
    makeConstraints
    -0.74
    akesh
    -0.73
    gemaakt
    -0.72
    angeran
    -0.68
    ofür
    -0.65
    zocht
    -0.65
    adple
    -0.65
     Praze
    -0.64
    voyance
    -0.64
    POSITIVE LOGITS
    ization
    1.24
    ized
    1.17
    Northern
    1.08
     Northern
    1.03
    isation
    1.00
     Southern
    0.99
    FER
    0.97
    Southern
    0.96
    {(\
    0.96
     NORTHERN
    0.95
    Activations Density 0.043%

    No Known Activations