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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 4509
    Prev
    Next
    INDEX
    Explanations

    references to election results and political accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Byz
    -0.40
    dets
    -0.40
     vere
    -0.39
     reseñas
    -0.39
     Seder
    -0.38
     mex
    -0.38
    tops
    -0.38
    Chain
    -0.37
     Pest
    -0.37
    chain
    -0.37
    POSITIVE LOGITS
     political
    1.04
    political
    0.92
     opposition
    0.92
    Opposition
    0.91
     Opposition
    0.89
     Political
    0.88
    GraphicsUnit
    0.86
    Political
    0.86
    opposition
    0.84
     politi
    0.84
    Activations Density 0.097%

    No Known Activations