© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10871
    Prev
    Next
    INDEX
    Explanations

    references to products or product descriptions

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

    the word "product"

    np_acts-logits-general · gemini-2.0-flash

    product development, details, information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    IntoConstraints
    -0.73
    AnchorStyles
    -0.68
     /\.(
    -0.60
     InputDecoration
    -0.59
    ISTRATION
    -0.58
    ities
    -0.57
    encre
    -0.56
    cales
    -0.56
    ใจ
    -0.53
    ciled
    -0.53
    POSITIVE LOGITS
     products
    1.19
     Products
    1.02
     getProduct
    0.95
    products
    0.94
    Products
    0.92
     product
    0.92
     PRODUCTS
    0.91
    getProducts
    0.90
     产品
    0.87
     Product
    0.86
    Activations Density 0.056%

    No Known Activations