© 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. 16-GEMMASCOPE-RES-16K
    11. 14297
    Prev
    Next
    INDEX
    Explanations

    themes related to violence and human suffering

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

    politics, government, or global issues

    np_acts-logits-general · gemini-2.0-flash

    political action and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кои
    -0.51
     magát
    -0.51
    agissait
    -0.50
     disponibilité
    -0.49
     gost
    -0.48
    Карьера
    -0.47
     biztos
    -0.47
     chi̍t
    -0.46
     cielos
    -0.46
     correctes
    -0.46
    POSITIVE LOGITS
     political
    0.88
     politicians
    0.79
     '\\;'
    0.75
     politics
    0.75
    expandindo
    0.74
     geopolitical
    0.72
     governments
    0.69
     global
    0.68
     world
    0.67
    political
    0.67
    Activations Density 0.366%

    No Known Activations