© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    narratives or personal anecdotes that involve interactions with diverse cultural backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apapun
    -0.78
     quaisquer
    -0.65
     akár
    -0.65
     enää
    -0.63
     podendo
    -0.62
     vertrou
    -0.57
     any
    -0.57
     любых
    -0.56
     tetap
    -0.55
     qualunque
    -0.55
    POSITIVE LOGITS
     recently
    0.90
    recently
    0.77
    たまたま
    0.69
    Recently
    0.68
     quite
    0.67
     récemment
    0.65
     iirc
    0.63
     Recently
    0.63
     недавно
    0.63
     someone
    0.62
    Activations Density 0.820%

    No Known Activations