© 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. 22-GEMMASCOPE-RES-16K
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    elements related to personal relationships and social connections

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

    Follows a name, often capitalized

    np_acts-logits-general · gemini-2.0-flash

    Kiki and female names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jambe
    -0.50
     Gill
    -0.49
     BI
    -0.48
     MatDialog
    -0.48
    BI
    -0.47
     PP
    -0.47
    Gill
    -0.47
    endpush
    -0.47
     Mol
    -0.47
    arrant
    -0.46
    POSITIVE LOGITS
     Hilton
    0.85
     Fletcher
    0.80
     Breslau
    0.75
     Steffen
    0.72
     Aladdin
    0.70
     Whitfield
    0.69
     Lune
    0.69
     Fenton
    0.69
     marion
    0.68
     Nathaniel
    0.68
    Activations Density 0.555%

    No Known Activations