© 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. 28-GEMMASCOPE-RES-16K
    6. 8503
    Prev
    Next
    INDEX
    Explanations

    brands and manufacturers of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after company names or brands

    np_acts-logits-general · gemini-2.0-flash

    manufacturers and brands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mortgage
    -0.54
     Maturity
    -0.53
     Banking
    -0.53
     シャンプー
    -0.53
    Mortgage
    -0.52
     Insurance
    -0.51
     Grocery
    -0.50
     underwriting
    -0.50
     mortgage
    -0.50
     bluzka
    -0.50
    POSITIVE LOGITS
     manufacturer
    0.68
     manufacturers
    0.66
     brands
    0.64
     fabricante
    0.63
     Hersteller
    0.62
     fabricant
    0.61
     manufactures
    0.60
     marchio
    0.59
     brand
    0.58
     manufactured
    0.58
    Activations Density 0.404%

    No Known Activations