© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16368
    Prev
    Next
    INDEX
    Explanations

    elements and discussions related to corruption and legal accusations in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Derbyniad
    -0.38
    WithIOException
    -0.35
     mergeFrom
    -0.35
    PreferredItem
    -0.35
    formats
    -0.33
    dafx
    -0.33
    exitRule
    -0.32
     AppCompatTheme
    -0.32
     merken
    -0.32
     truyền
    -0.31
    POSITIVE LOGITS
     corruption
    1.26
     scandal
    1.16
    corruption
    1.12
     corrupt
    1.11
     allegations
    1.10
     scandals
    1.10
    Corruption
    1.09
     Corruption
    1.03
     corrupción
    1.01
     bribery
    1.00
    Activations Density 1.498%

    No Known Activations