© 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. 30-GEMMASCOPE-RES-16K
    11. 9804
    Prev
    Next
    INDEX
    Explanations

    instances of corruption and illegal activities related to political officials

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

    corruption and bribery

    np_acts-logits-general · gemini-2.0-flash

    corruption and bribery schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.54
    buffer
    -0.40
    PreferredItem
    -0.40
     Jehová
    -0.40
    runOnUiThread
    -0.39
     Juifs
    -0.39
     calculées
    -0.39
     Partager
    -0.38
    uidado
    -0.38
     dieux
    -0.38
    POSITIVE LOGITS
     corruption
    1.95
     Corruption
    1.70
    Corruption
    1.69
     corrupt
    1.64
    corruption
    1.63
     corrupción
    1.49
     corrup
    1.48
     bribery
    1.35
     corrupted
    1.25
     corrom
    1.23
    Activations Density 0.556%

    No Known Activations