© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7801
    Prev
    Next
    INDEX
    Explanations

    terms related to corruption and bribery

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

    Bribes, corruption, and illicit payments

    np_acts-logits-general · gemini-2.0-flash

    bribery and corruption offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.63
     autorytatywna
    -0.58
    awtextra
    -0.54
     surla
    -0.50
    ThroughAttribute
    -0.45
    ttemberg
    -0.44
     StatefulWidget
    -0.43
    UseVisualStyle
    -0.41
    occuper
    -0.41
    ükü
    -0.40
    POSITIVE LOGITS
     bribe
    1.27
     bribes
    1.24
     bribery
    1.20
     bri
    0.96
    賄
    0.90
    贿
    0.90
     corrup
    0.83
     corrupt
    0.83
     corruption
    0.80
     corrom
    0.80
    Activations Density 0.458%

    No Known Activations