© 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. 11-GEMMASCOPE-RES-16K
    11. 1448
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding historical injustices and their implications, particularly involving accountability and societal guilt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.71
    Numerology
    -0.57
     EconPapers
    -0.56
    EndContext
    -0.55
    וויק
    -0.53
     <=",
    -0.51
     ujednoznacz
    -0.51
    wór
    -0.51
    ModelSerializer
    -0.51
    ləş
    -0.50
    POSITIVE LOGITS
     keter
    0.56
    IVEREF
    0.55
     StatefulWidget
    0.53
    httphttps
    0.52
     InputDecoration
    0.50
     darin
    0.48
     includes
    0.48
    Einzelnachweise
    0.47
    ׂ
    0.46
    /**
    0.46
    Activations Density 0.799%

    No Known Activations