© 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. 2256
    Prev
    Next
    INDEX
    Explanations

    special characters and specific formatting commonly found in technical or legal documents

    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
     Gothenburg
    -0.65
     McKe
    -0.63
     Morin
    -0.59
     Farr
    -0.57
     Daryl
    -0.56
     Ronda
    -0.55
     Eko
    -0.54
     Pompeii
    -0.52
     Barba
    -0.52
     Angelina
    -0.52
    POSITIVE LOGITS
     Mey
    0.59
     Trist
    0.55
    Mey
    0.55
    elemField
    0.55
     Barclay
    0.54
    UnitTesting
    0.54
    ViewInit
    0.53
     Marlow
    0.53
     Samson
    0.52
    Samson
    0.52
    Activations Density 2.072%

    No Known Activations