© 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. 18-GEMMASCOPE-RES-16K
    11. 6339
    Prev
    Next
    INDEX
    Explanations

    references to people, particularly names and surnames

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

    East Asian names: Han, Kim, Liu, Cao

    np_acts-logits-general · gemini-2.0-flash

    East Asian surnames and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.84
     Cæsar
    -0.80
     Theſe
    -0.76
     faſt
    -0.76
     Houſe
    -0.76
     myſelf
    -0.72
     Conſ
    -0.70
     Beſ
    -0.69
     pleaſure
    -0.69
     חיצוניים
    -0.66
    POSITIVE LOGITS
     Y
    0.63
     J
    0.61
     M
    0.58
     createState
    0.55
    brothers
    0.54
     brothers
    0.53
    Спасылкі
    0.53
     rodin
    0.53
     Brothers
    0.52
     beginnetje
    0.52
    Activations Density 0.057%

    No Known Activations