© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 576
    Prev
    Next
    INDEX
    Explanations

    mentions of products and related information

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

    words related to "product" and commerce.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cérebro
    -0.45
    6
    -0.44
     provisoire
    -0.44
    Cuándo
    -0.43
     necessárias
    -0.42
     invierno
    -0.42
     sechs
    -0.42
     democrática
    -0.41
     fears
    -0.41
     confiança
    -0.41
    POSITIVE LOGITS
     product
    1.17
     Product
    1.16
    Product
    1.11
     getProduct
    1.09
    product
    1.09
     Products
    1.01
     PRODUCT
    1.00
    getProduct
    0.99
     products
    0.97
    ProductService
    0.96
    Activations Density 0.036%

    No Known Activations