© 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. 16-GEMMASCOPE-RES-16K
    11. 7146
    Prev
    Next
    INDEX
    Explanations

    text discussing health-related topics, especially chronic conditions and treatments

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

    Text or topics related to book chapters/sections

    np_acts-logits-general · gemini-2.0-flash

    structure of written works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.58
    
    -0.57
     AssemblyCulture
    -0.57
    tvguidetime
    -0.56
     elbows
    -0.55
    TagMode
    -0.55
    Release
    -0.53
    nloa
    -0.53
     grossa
    -0.52
    semantics
    -0.52
    POSITIVE LOGITS
     chapter
    0.90
     chapters
    0.83
    chapter
    0.79
     paragraphs
    0.78
     paragraph
    0.75
     section
    0.74
     Chapter
    0.71
     discusses
    0.66
     devotes
    0.66
    Chapter
    0.66
    Activations Density 1.327%

    No Known Activations