© 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. 7423
    Prev
    Next
    INDEX
    Explanations

    references to duality and opposing sides

    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
     bū
    -0.31
    Biografi
    -0.31
     peu
    -0.30
     promotion
    -0.30
     little
    -0.29
     among
    -0.28
    깨
    -0.28
     Kenney
    -0.28
    Promotion
    -0.28
     Gaff
    -0.28
    POSITIVE LOGITS
     side
    1.20
     Side
    1.15
    side
    1.15
    Side
    1.10
     SIDE
    1.09
     sides
    1.04
     Sides
    1.01
    sides
    1.00
    SIDE
    0.99
    sided
    0.96
    Activations Density 0.336%

    No Known Activations