© 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. 17-GEMMASCOPE-RES-16K
    11. 11428
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to immigration, particularly illegal immigration and demographics associated with Hispanic and Latino populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Araújo
    -0.93
     Guimarães
    -0.87
     Egli
    -0.83
     Branco
    -0.83
     Vitória
    -0.83
     Maggiore
    -0.82
     Bretagne
    -0.80
     Olímp
    -0.80
     Afonso
    -0.78
     Jehová
    -0.78
    POSITIVE LOGITS
     de
    0.64
    Билгалдахарш
    0.63
     Mexican
    0.61
    scriptcase
    0.60
    Hispanic
    0.59
     Мекси
    0.57
     Hispanic
    0.57
     qu
    0.51
     Mexico
    0.51
    Mexican
    0.51
    Activations Density 0.474%

    No Known Activations