© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7858
    Prev
    Next
    INDEX
    Explanations

    promotional phrases related to discounts and offers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OCCURRED
    -0.54
    Derbyniad
    -0.50
     transférez
    -0.44
    Personensuche
    -0.44
    MessageTagHelper
    -0.43
    AccessorTable
    -0.43
    AutoField
    -0.43
     transfieras
    -0.42
     autorytatywna
    -0.41
    ViewInit
    -0.40
    POSITIVE LOGITS
     discounts
    1.59
     discount
    1.55
     deals
    1.52
     Deals
    1.34
     deal
    1.33
     Discounts
    1.30
     discounted
    1.27
     Discount
    1.27
    discount
    1.22
     promotions
    1.20
    Activations Density 0.290%

    No Known Activations