© 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. 8500
    Prev
    Next
    INDEX
    Explanations

    technical components and specifications related to home appliances

    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
     stället
    -0.56
     Verhältnisse
    -0.51
     Vernunft
    -0.50
     niebla
    -0.49
     Sünde
    -0.47
     hogares
    -0.46
     incendios
    -0.45
     varandra
    -0.45
     automóviles
    -0.45
     mentiras
    -0.45
    POSITIVE LOGITS
     cables
    1.32
     screws
    1.24
     wires
    1.23
     hoses
    1.19
     bolts
    1.13
     gaskets
    1.13
     hinges
    1.13
     fasteners
    1.12
     electrodes
    1.11
     lenses
    1.09
    Activations Density 1.226%

    No Known Activations