© 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. 7922
    Prev
    Next
    INDEX
    Explanations

    mentions of educational themes and initiatives

    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
     únicamente
    -0.50
     către
    -0.50
     agujas
    -0.49
     fuerzas
    -0.48
     Leuten
    -0.47
     asuntos
    -0.47
     muchísimo
    -0.47
     enamorado
    -0.47
     sesiones
    -0.46
     orejas
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.83
    ...".
    0.82
     ...'
    0.76
     שוליים
    0.75
    ...";
    0.73
     EconPapers
    0.73
    ...',
    0.72
    tvguidetime
    0.72
    ...",
    0.72
    …’
    0.69
    Activations Density 0.492%

    No Known Activations