© 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. 28-GEMMASCOPE-RES-16K
    11. 2887
    Prev
    Next
    INDEX
    Explanations

    references to international organizations and treaties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    United Nations and related organizations

    np_acts-logits-general · gemini-2.0-flash

    international organizations like UN and WHO

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADELPHIA
    -0.48
    ioutil
    -0.46
    RegressionTest
    -0.45
    İstinadlar
    -0.43
    ReusableCell
    -0.42
    Manbalar
    -0.41
    webElementXpaths
    -0.40
    WithIOException
    -0.40
    impianto
    -0.40
    windowFixed
    -0.40
    POSITIVE LOGITS
     UN
    1.17
     UNESCO
    1.13
     World
    1.05
     WHO
    1.00
     Unesco
    0.93
    UNESCO
    0.93
    World
    0.88
    UN
    0.86
     International
    0.84
    WHO
    0.82
    Activations Density 0.206%

    No Known Activations