© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4829
    Prev
    Next
    INDEX
    Explanations

    mentions of government and public institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.81
     himo
    -0.73
    Rüyada
    -0.69
     AllMovie
    -0.64
     Himo
    -0.64
    ttino
    -0.57
    DebuggerNonUser
    -0.57
    ratore
    -0.57
    adalajara
    -0.56
    GEBURTSDATUM
    -0.56
    POSITIVE LOGITS
     government
    0.94
     governments
    0.76
     Government
    0.76
     governmental
    0.75
     federal
    0.72
     Federal
    0.70
    government
    0.69
     National
    0.68
     pemerintah
    0.67
    Government
    0.66
    Activations Density 0.683%

    No Known Activations