© 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. 20-GEMMASCOPE-RES-16K
    11. 1095
    Prev
    Next
    INDEX
    Explanations

    variations of the word "people"

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

    starting with "Pe" or "pe"

    np_acts-logits-general · gemini-2.0-flash

    Pe, people, names

    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
    extAlignment
    -0.96
     Normdatei
    -0.86
     InputDecoration
    -0.85
    UrlResolution
    -0.78
    StoryboardSegue
    -0.78
    __*/
    -0.75
     Diony
    -0.71
    Cyfeiriadau
    -0.69
    =?";
    -0.69
    Bibliograf
    -0.68
    POSITIVE LOGITS
    Pe
    0.68
     Pe
    0.68
     pe
    0.65
     lâng
    0.65
    haps
    0.60
     peek
    0.48
     пе
    0.47
     PE
    0.47
     ople
    0.47
    jspx
    0.46
    Activations Density 0.117%

    No Known Activations