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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 13579
    Prev
    Next
    INDEX
    Explanations

    references to online shopping and customer service attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    newtheorem
    -0.64
    utilisons
    -0.62
     disponibilités
    -0.61
    MLLoader
    -0.60
    Personendaten
    -0.60
    setVerticalGroup
    -0.59
     InputDecoration
    -0.59
     ComVisible
    -0.58
    libatkan
    -0.58
    MessageTagHelper
    -0.57
    POSITIVE LOGITS
     desertcart
    0.66
     shopping
    0.54
    desertcart
    0.51
    shopping
    0.45
     Shopping
    0.44
     shipping
    0.43
     widest
    0.40
     Mall
    0.40
     millions
    0.39
     lowest
    0.37
    Activations Density 0.125%

    No Known Activations