© 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. 11-GEMMASCOPE-RES-16K
    11. 5288
    Prev
    Next
    INDEX
    Explanations

    technical terms and keywords relating to data sheets and device compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.56
     '\\;'
    -0.55
     &___
    -0.52
     NDEBUG
    -0.46
     AssemblyProduct
    -0.46
     parachoque
    -0.45
     sofá
    -0.44
    /*++
    -0.42
     transférez
    -0.41
    osocial
    -0.41
    POSITIVE LOGITS
     пос
    0.41
     serena
    0.41
    GetMapping
    0.39
    Хьажоргаш
    0.38
     pinulongan
    0.38
    ñales
    0.38
    flashdata
    0.37
    hoots
    0.37
     eas
    0.37
    parsedMessage
    0.37
    Activations Density 0.759%

    No Known Activations