© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 5719
    Prev
    Next
    INDEX
    Explanations

    references to political power dynamics and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ️⃣
    -0.41
     otomatig
    -0.40
    jewództ
    -0.40
    紐
    -0.38
     latina
    -0.38
     Rhine
    -0.37
     mexican
    -0.37
    gangssprach
    -0.36
    ChildScrollView
    -0.36
     Menschheit
    -0.36
    POSITIVE LOGITS
     nationalist
    0.89
     Islamist
    0.82
     smuggled
    0.79
     Nationalist
    0.79
     nationalists
    0.77
    Corruption
    0.77
     Corruption
    0.73
     impunity
    0.72
    corruption
    0.71
     corruption
    0.69
    Activations Density 1.296%

    No Known Activations