© 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. 5-GEMMASCOPE-RES-16K
    11. 1147
    Prev
    Next
    INDEX
    Explanations

    HTML title tags and their content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.69
     iParam
    -0.68
    gridColumn
    -0.67
     daarvan
    -0.61
    WriteBarrier
    -0.60
     sztuki
    -0.60
     okuyayım
    -0.57
     vVar
    -0.56
     gjø
    -0.56
     vägen
    -0.56
    POSITIVE LOGITS
    title
    1.92
     title
    1.40
    TITLE
    1.31
    Title
    1.31
     Title
    1.15
     TITLE
    1.10
    setTitle
    1.02
    getTitle
    0.96
     titel
    0.93
     titles
    0.87
    Activations Density 0.034%

    No Known Activations