© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 10249
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and their characteristics within Vietnam

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Israel
    -0.40
     Brit
    -0.38
     enfans
    -0.35
     Pass
    -0.35
    JCheckBox
    -0.34
     Kanada
    -0.33
    IsPostBack
    -0.33
     Hebrew
    -0.33
     Red
    -0.33
     loose
    -0.33
    POSITIVE LOGITS
    تقاوى
    0.66
     CanadaChoose
    0.65
    ArrowToggle
    0.63
     Vietnamese
    0.58
    Vietnam
    0.57
    IntoConstraints
    0.56
    Vietnamese
    0.56
     Vietnam
    0.53
    namese
    0.52
     ligiloj
    0.52
    Activations Density 0.067%

    No Known Activations