© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 13604
    Prev
    Next
    INDEX
    Explanations

    references to the Chinese ethnic group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nark
    -0.84
    nson
    -0.74
     démocr
    -0.73
    𝐯
    -0.73
     متعلقه
    -0.73
     millón
    -0.73
    стоин
    -0.72
     uova
    -0.71
     ***!
    -0.71
     Chwiliwch
    -0.71
    POSITIVE LOGITS
    yli
    0.86
     Chinese
    0.82
    olese
    0.82
    adecimal
    0.81
     Maltese
    0.81
     rouges
    0.81
    anese
    0.80
    Vietnamese
    0.76
    OES
    0.76
     Vietnamese
    0.75
    Activations Density 0.032%

    No Known Activations