© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5936
    Prev
    Next
    INDEX
    Explanations

    business-related concepts and discussions

    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
    +#+#
    -0.54
    AddTagHelper
    -0.48
     wikipagina
    -0.44
     للاسماء
    -0.40
     manuten
    -0.40
    dziew
    -0.38
    ленность
    -0.37
     remboursement
    -0.36
    PerformLayout
    -0.36
     étrang
    -0.36
    POSITIVE LOGITS
     vehicle
    1.42
     vehicles
    1.27
     conduit
    1.17
    vehicle
    1.14
     mechanism
    1.11
     vehículo
    1.10
     Vehicles
    1.08
     veículo
    1.05
     catalyst
    1.03
    vehicles
    1.03
    Activations Density 0.800%

    No Known Activations