© 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. 11619
    Prev
    Next
    INDEX
    Explanations

    references to political accountability and corruption scandals

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

    Follows "was" or "her"

    np_acts-logits-general · gemini-2.0-flash

    assistants and advisors

    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
     Bapak
    -0.38
    roek
    -0.33
    君
    -0.33
    leitung
    -0.33
     GUY
    -0.33
    Вла
    -0.32
     gốc
    -0.32
    Emperor
    -0.32
     PRESIDENT
    -0.32
     ruler
    -0.32
    POSITIVE LOGITS
     assistants
    1.51
     assistant
    1.30
     aides
    1.22
     Assistants
    1.21
     helpers
    1.09
    assistant
    1.08
     Assistant
    1.02
     bodyguard
    1.02
     advisors
    0.98
    Assistant
    0.97
    Activations Density 0.558%

    No Known Activations