© 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. 9-GEMMASCOPE-RES-16K
    6. 8702
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to retail businesses and commerce

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wolf
    -0.45
     UNESCO
    -0.45
     Commander
    -0.45
     Boyer
    -0.43
     Bogdan
    -0.43
     AttributeSet
    -0.42
    alamualaikum
    -0.42
     commandant
    -0.41
     WOLF
    -0.41
    Dokument
    -0.41
    POSITIVE LOGITS
     retail
    1.86
    Retail
    1.84
     Retail
    1.82
     RETAIL
    1.75
    retail
    1.75
     retailing
    1.40
    零售
    1.35
     retailers
    1.20
     retailer
    1.20
     Retailers
    1.20
    Activations Density 0.144%

    No Known Activations