© 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. 23-GEMMASCOPE-RES-16K
    11. 1690
    Prev
    Next
    INDEX
    Explanations

    references to specific layers or components in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bradshaw
    -0.34
    astéroïdes
    -0.32
    glBegin
    -0.29
     bancada
    -0.29
     embers
    -0.29
     épar
    -0.28
     cuenca
    -0.28
    OCCURRED
    -0.28
     colgante
    -0.28
     partecip
    -0.27
    POSITIVE LOGITS
     layers
    1.08
     layer
    1.02
     Layers
    0.99
     Layer
    0.92
    Layers
    0.89
    layer
    0.89
    layers
    0.87
     layering
    0.86
     layered
    0.86
     LAYER
    0.85
    Activations Density 0.869%

    No Known Activations