© 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. 3318
    Prev
    Next
    INDEX
    Explanations

    terms related to control and data management

    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
     brasileño
    -0.94
     portugués
    -0.75
     literario
    -0.73
     secundario
    -0.72
     fotográfico
    -0.71
     extranjera
    -0.70
     universitarios
    -0.69
     universitario
    -0.68
     productivo
    -0.67
     diaria
    -0.66
    POSITIVE LOGITS
     interp
    0.46
     sider
    0.44
     transit
    0.43
     paradox
    0.41
     contrast
    0.41
     dali
    0.40
     tanto
    0.40
     transversal
    0.40
     nos
    0.39
     radic
    0.39
    Activations Density 0.088%

    No Known Activations