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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13797
    Prev
    Next
    INDEX
    Explanations

    elements related to pagination and data retrieval in a programming context

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

    Pagination, page numbers, or page-related elements

    np_acts-logits-general · gemini-2.0-flash

    page numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UniformLocation
    -0.55
    
    -0.55
    XmlEnum
    -0.52
    prnewswire
    -0.52
    HKEY
    -0.51
    RuleContext
    -0.49
    InputBorder
    -0.49
    TALL
    -0.47
    CodeAttribute
    -0.46
    oulli
    -0.46
    POSITIVE LOGITS
     page
    1.57
    Page
    1.50
     Page
    1.47
    page
    1.41
    PAGE
    1.33
     PAGE
    1.32
     pages
    1.32
     pag
    1.29
     pagination
    1.19
     pagina
    1.19
    Activations Density 0.190%

    No Known Activations