© 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. 24-GEMMASCOPE-RES-16K
    11. 3968
    Prev
    Next
    INDEX
    Explanations

    references to American foreign interventions and their consequences

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

    Geopolitics, power, and international relations

    np_acts-logits-general · gemini-2.0-flash

    geopolitical strategy and conflict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 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
     Sodom
    -0.62
     suel
    -0.56
     Statisti
    -0.55
     décret
    -0.55
     CreateTagHelper
    -0.55
    ########.
    -0.54
    avra
    -0.54
    angana
    -0.54
     expéri
    -0.54
    ietal
    -0.54
    POSITIVE LOGITS
     security
    0.87
     geo
    0.81
     geopolitical
    0.78
     strategic
    0.74
    geo
    0.72
     Security
    0.70
    security
    0.70
     regional
    0.69
    Security
    0.68
    ipolar
    0.65
    Activations Density 0.231%

    No Known Activations