© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 2924
    Prev
    Next
    INDEX
    Explanations

    references to discounts and coupon codes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    words commonly found in spam or low-quality generated text about discount codes and promotional offers.

    oai_token-act-pair · claude-4-5-haiku
    Triggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     étoient
    -0.44
     appelez
    -0.40
    تل
    -0.39
    Italic
    -0.37
    kjø
    -0.36
    Implicit
    -0.36
     تل
    -0.36
     Ricci
    -0.35
     hic
    -0.35
     uș
    -0.35
    POSITIVE LOGITS
    MigrationBuilder
    0.62
    transQ
    0.54
     resourceCulture
    0.53
    RegressionTest
    0.50
    EndInit
    0.45
     CreateTagHelper
    0.45
     بيها
    0.45
    Personendaten
    0.45
    ActionCreators
    0.44
    LayoutStyle
    0.44
    Activations Density 0.176%

    No Known Activations