© 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. 33-GEMMASCOPE-RES-16K
    11. 11212
    Prev
    Next
    INDEX
    Explanations

    activities related to networking and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.48
     désolés
    -0.47
     forState
    -0.44
     calldata
    -0.40
     Verantwortung
    -0.39
    parsedMessage
    -0.39
    LookAnd
    -0.38
     تضيفلها
    -0.38
    IsContent
    -0.37
     viewDidLoad
    -0.37
    POSITIVE LOGITS
     networking
    2.19
     network
    2.02
     networks
    1.94
     Networking
    1.85
    Networking
    1.75
    network
    1.74
    networking
    1.73
     NETWORK
    1.71
     contacts
    1.66
     Network
    1.63
    Activations Density 0.448%

    No Known Activations