© 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 EvalsExportsinterp-engineNEWAPI 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. 8723
    Prev
    Next
    INDEX
    Explanations

    musical elements and instruments

    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
     للاسماء
    -0.40
     piscinas
    -0.40
    клопе
    -0.38
     Normdatei
    -0.37
    asteroide
    -0.37
     Roskov
    -0.37
    ROCK
    -0.37
    Története
    -0.36
    Autoritní
    -0.36
     precipitates
    -0.36
    POSITIVE LOGITS
     folk
    0.87
     Traditional
    0.84
     traditional
    0.81
    Traditional
    0.80
     Folk
    0.79
    Folk
    0.77
    folk
    0.74
    traditional
    0.73
     folklor
    0.66
     banjo
    0.66
    Activations Density 0.248%

    No Known Activations