© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5591
    Prev
    Next
    INDEX
    Explanations

    references to global or international topics

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

    global or international scope

    np_acts-logits-general · gemini-2.0-flash

    global scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.68
    Maryland
    -0.57
     TestBed
    -0.56
    Ohio
    -0.54
    WithIOException
    -0.53
     CURIAM
    -0.53
    ViewFeatures
    -0.52
    ikusbot
    -0.52
    astanza
    -0.50
    tvguidetime
    -0.50
    POSITIVE LOGITS
     international
    1.14
     global
    1.13
     worldwide
    1.09
     countries
    0.99
     world
    0.97
    global
    0.96
     globally
    0.95
     mundial
    0.93
    international
    0.93
     Global
    0.92
    Activations Density 0.762%

    No Known Activations