© 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. 10462
    Prev
    Next
    INDEX
    Explanations

    components and structures related to engineering or technical setups

    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
     inward
    -0.43
    zeptember
    -0.36
     megh
    -0.36
    posables
    -0.35
    queryInterface
    -0.35
    Введение
    -0.35
     input
    -0.34
     intr
    -0.33
     ingestion
    -0.33
    input
    -0.32
    POSITIVE LOGITS
     exit
    1.94
     salida
    1.78
     output
    1.77
     Exit
    1.75
     exits
    1.63
     Output
    1.60
     keluar
    1.60
     exiting
    1.59
    exit
    1.59
    Exit
    1.55
    Activations Density 0.949%

    No Known Activations