© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 7290
    Prev
    Next
    INDEX
    Explanations

    references to resources and their management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Noviembre
    -0.47
     París
    -0.47
     conformidad
    -0.45
     Deixe
    -0.44
    LookAnd
    -0.43
     Descubre
    -0.43
     Redacción
    -0.43
    queryInterface
    -0.43
     Reglamento
    -0.42
     Ayuntamiento
    -0.41
    POSITIVE LOGITS
     resource
    1.31
     Resource
    1.27
     RESOURCE
    1.25
    Resource
    1.17
    resource
    1.16
     resources
    1.16
     Resources
    1.15
     ressource
    1.13
    RESOURCE
    1.12
     RESOURCES
    1.07
    Activations Density 0.098%

    No Known Activations