© 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. 15249
    Prev
    Next
    INDEX
    Explanations

    specific identifiers and keywords related to programming and data structures

    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
     Majefty
    -0.96
     pleaſure
    -0.90
     Efq
    -0.65
     ſta
    -0.63
     ſever
    -0.63
     fubject
    -0.61
     deſt
    -0.60
     purpoſe
    -0.60
     Chriftian
    -0.59
     ſol
    -0.59
    POSITIVE LOGITS
    s
    1.09
    es
    1.03
    bs
    0.95
    ks
    0.91
    os
    0.90
    ens
    0.89
    nes
    0.88
    as
    0.87
    fs
    0.86
    BS
    0.86
    Activations Density 2.349%

    No Known Activations