© 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. 7018
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental issues and regulations

    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
     aspect
    -0.67
     situation
    -0.66
     subset
    -0.66
     multitude
    -0.65
    undrum
    -0.63
     timeline
    -0.63
     standpoint
    -0.61
     dataset
    -0.60
     portion
    -0.60
     mixture
    -0.60
    POSITIVE LOGITS
     versions
    0.79
     quantities
    0.65
     situations
    0.63
     notions
    0.63
     levels
    0.62
     opportunities
    0.62
     amounts
    0.62
     relationships
    0.61
     methods
    0.60
     programs
    0.60
    Activations Density 2.181%

    No Known Activations