© 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 - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5813
    Prev
    Next
    INDEX
    Explanations

    references to nationalities or ethnic identities, particularly Italian, British, German, and Jewish

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.75
     للمعارف
    -0.67
    setVerticalGroup
    -0.66
    rrggbb
    -0.62
    olescence
    -0.61
    GMENT
    -0.60
     AFRICA
    -0.59
    roek
    -0.58
    amling
    -0.58
    liceerd
    -0.58
    POSITIVE LOGITS
     Polish
    1.77
     Italian
    1.74
     Brazilian
    1.70
     Romanian
    1.70
     Hungarian
    1.70
     Mexican
    1.67
     German
    1.66
     Swedish
    1.65
     Japanese
    1.63
     Indonesian
    1.62
    Activations Density 0.131%

    No Known Activations