© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5371
    Prev
    Next
    INDEX
    Explanations

    references to artistic and electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     technique
    -0.40
     Doctrine
    -0.36
     doctrine
    -0.36
     phenomenon
    -0.35
    UserRepository
    -0.34
     درد
    -0.32
     Karim
    -0.32
     audiencia
    -0.30
     atro
    -0.30
     intimacy
    -0.30
    POSITIVE LOGITS
     devices
    1.13
     appliances
    1.10
     Devices
    1.00
     Appliances
    0.99
    devices
    0.92
     DEVICES
    0.88
    Devices
    0.86
     gadgets
    0.78
     appliance
    0.75
     aparatos
    0.69
    Activations Density 0.090%

    No Known Activations