© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2195
    Prev
    Next
    INDEX
    Explanations

    references to government agencies and their operations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Following "the" and referring to government entities

    np_acts-logits-general · gemini-2.0-flash

    federal government agencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    WriteBarrier
    -0.65
     surla
    -0.60
    wifery
    -0.60
    XmlAccessType
    -0.57
    ształ
    -0.55
     indígena
    -0.54
    gemeester
    -0.52
    yntaxException
    -0.52
    tituzione
    -0.52
    fromnode
    -0.51
    POSITIVE LOGITS
     Department
    1.19
     federal
    1.08
     Federal
    1.07
    Department
    1.03
     Centers
    0.99
     US
    0.96
     Dept
    0.94
    Federal
    0.92
     Departments
    0.89
     USDA
    0.88
    Activations Density 0.500%

    No Known Activations