© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5694
    Prev
    Next
    INDEX
    Explanations

    dates and specific numerical references related to legal or official 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
     Sunday
    -0.93
    Sunday
    -0.90
     Sundays
    -0.83
     sunday
    -0.82
     Saturday
    -0.78
    Saturday
    -0.77
     SUNDAY
    -0.77
    SUNDAY
    -0.73
    Dimanche
    -0.69
    sunday
    -0.68
    POSITIVE LOGITS
    kháu
    0.53
    RenderAtEndOf
    0.52
    Demografie
    0.51
    fromnode
    0.46
    httphttps
    0.45
    +#+#
    0.44
    uxxxx
    0.44
    GTCX
    0.43
    RTSN
    0.41
    GEBURTS
    0.40
    Activations Density 0.309%

    No Known Activations