© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 13395
    Prev
    Next
    INDEX
    Explanations

    terms associated with organizational titles and roles in formal institutions

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

    autonomous institutions and authorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.71
     pleaſure
    -0.66
     Polsek
    -0.59
    لينكات
    -0.56
     purpoſe
    -0.54
     fubject
    -0.53
     uſed
    -0.52
    swick
    -0.52
     viſ
    -0.50
     houſe
    -0.50
    POSITIVE LOGITS
     board
    0.70
     Authority
    0.62
     corporation
    0.62
     agency
    0.59
     Corporation
    0.59
     Board
    0.58
     authority
    0.57
     boards
    0.54
    board
    0.53
     corporations
    0.52
    Activations Density 0.062%

    No Known Activations