Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1519
    Prev
    Next
    INDEX
    Explanations

    elements related to targeted advertising strategies and market segmentation

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

    a target audience or purpose

    np_acts-logits-general · gemini-2.0-flash

    target audience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Infórmanos
    -0.60
    phosa
    -0.60
     архивлан
    -0.51
    SceneManagement
    -0.50
    GEBURTSDATUM
    -0.50
    WindowConstants
    -0.50
    ьаж
    -0.50
    CloseOperation
    -0.50
    nantes
    -0.49
     ویکی‌پدیا
    -0.48
    POSITIVE LOGITS
     target
    2.06
     targeting
    1.99
     targeted
    1.84
    target
    1.84
     Targeting
    1.72
    Target
    1.69
     Target
    1.68
    targeting
    1.64
    targeted
    1.62
    Targeting
    1.60
    Activations Density 0.282%

    No Known Activations