© 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. 2537
    Prev
    Next
    INDEX
    Explanations

    instances of engagement and inquiry in conversational contexts

    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
     lecz
    -0.73
     poichè
    -0.72
     său
    -0.71
     gdyż
    -0.71
     אך
    -0.66
     tačiau
    -0.64
    sizeCache
    -0.63
     EconPapers
    -0.62
     endast
    -0.60
    IVEREF
    -0.59
    POSITIVE LOGITS
     somebody
    1.05
    somebody
    0.95
    Somebody
    0.91
     everybody
    0.88
     basically
    0.87
     Somebody
    0.87
    Anybody
    0.84
     maybe
    0.83
     anybody
    0.82
    basically
    0.79
    Activations Density 1.349%

    No Known Activations