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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1332
    Prev
    Next
    INDEX
    Explanations

    names of people and institutions

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

    Surnames followed by "&" or a company/institution

    np_acts-logits-general · gemini-2.0-flash

    brothers in 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
    SpringRunner
    -0.63
     espèce
    -0.50
    每个人
    -0.50
    яти
    -0.48
    tences
    -0.48
     binh
    -0.48
    ็จ
    -0.46
     ordinaire
    -0.45
    lorette
    -0.45
    uchsia
    -0.45
    POSITIVE LOGITS
     Brothers
    1.04
     Bros
    0.95
     brothers
    0.93
     County
    0.92
    Brothers
    0.84
    brothers
    0.83
     frères
    0.81
     BROTHERS
    0.80
     family
    0.80
     Family
    0.79
    Activations Density 0.567%

    No Known Activations