Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16225
    Prev
    Next
    INDEX
    Explanations

    references to historical military coups and their political impacts

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

    associated with political upheaval and regime change

    np_acts-logits-general · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    WithMany
    -0.56
    actéristique
    -0.48
    zysty
    -0.46
    viron
    -0.45
    reathe
    -0.44
    SharedCtor
    -0.44
    romyalgia
    -0.44
    CFC
    -0.43
    ReusableCell
    -0.42
    haviors
    -0.42
    POSITIVE LOGITS
     coup
    1.19
     overthrow
    1.18
     overthrown
    1.02
     revolution
    0.99
     coups
    0.93
     Coup
    0.85
     revolt
    0.85
    coup
    0.85
     rebellion
    0.84
     revolutions
    0.84
    Activations Density 0.325%

    No Known Activations