© 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. 10-GEMMASCOPE-RES-16K
    6. 1450
    Prev
    Next
    INDEX
    Explanations

    instances of governance and local decision-making in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.61
    Rcpp
    -0.58
    rends
    -0.58
    interopRequire
    -0.57
    jstor
    -0.54
    IndentedString
    -0.51
     (;;
    -0.51
    ActiveRecord
    -0.51
     QString
    -0.51
    gas
    -0.51
    POSITIVE LOGITS
    batore
    0.80
    LSU
    0.73
    kuuta
    0.72
     Coimbatore
    0.72
     tamil
    0.71
     Tamil
    0.70
     Chennai
    0.70
     kerala
    0.69
     Kerala
    0.68
     Malayalam
    0.67
    Activations Density 0.141%

    No Known Activations