© 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. 10-GEMMASCOPE-RES-16K
    6. 11256
    Prev
    Next
    INDEX
    Explanations

    contexts discussing various services provided by businesses or establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plegable
    -0.47
     bancaire
    -0.46
     dourado
    -0.45
     Constitucional
    -0.45
     Inscrivez
    -0.45
     constitucional
    -0.43
     Estadual
    -0.42
     Cientí
    -0.41
     huge
    -0.40
     Ambiental
    -0.40
    POSITIVE LOGITS
     service
    1.80
     Service
    1.75
    service
    1.66
     SERVICE
    1.66
    Service
    1.55
     services
    1.52
    ervice
    1.50
    SERVICE
    1.48
     Services
    1.45
    services
    1.41
    Activations Density 0.085%

    No Known Activations