© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 12514
    Prev
    Next
    INDEX
    Explanations

    mentions of routine practices, particularly in the context of democracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guess
    -0.48
     guess
    -0.45
     gues
    -0.45
    Guess
    -0.45
     вікісторінку
    -0.44
     laterally
    -0.43
     guessing
    -0.43
    Nuorodos
    -0.43
    ความ
    -0.42
    borderWidth
    -0.42
    POSITIVE LOGITS
     democracy
    1.04
     Democracy
    0.97
     demon
    0.96
     Demon
    0.93
    Democracy
    0.88
    democracy
    0.85
    Demon
    0.81
    demon
    0.81
     DEMON
    0.79
     Demonstration
    0.76
    Activations Density 0.167%

    No Known Activations