© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8852
    Prev
    Next
    INDEX
    Explanations

    references to political figures, specifically focusing on controversies, investigations, and media coverage surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gatan
    -0.67
    enido
    -0.62
    principalColumn
    -0.60
    GARET
    -0.59
    endous
    -0.59
     Realme
    -0.58
    astify
    -0.58
    WebVitals
    -0.57
     Telegram
    -0.56
     يتيمه
    -0.56
    POSITIVE LOGITS
     Obama
    0.77
    Obama
    0.69
     Sarkozy
    0.64
     Huffington
    0.63
     Rossini
    0.62
    ulipas
    0.61
     HttpNotFound
    0.60
    しめ
    0.60
     foie
    0.60
     Kinect
    0.59
    Activations Density 0.821%

    No Known Activations