© 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. 10-GEMMASCOPE-RES-16K
    11. 5950
    Prev
    Next
    INDEX
    Explanations

    financial data and statements related to balance sheets and cash positions

    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
    -};
    -0.42
    outWeight
    -0.42
     cập
    -0.36
    WriteTagHelper
    -0.35
     épic
    -0.33
    хьтан
    -0.33
    putExtra
    -0.33
     monkeys
    -0.33
     vertraut
    -0.33
    Према
    -0.32
    POSITIVE LOGITS
    SequentialGroup
    0.62
     assets
    0.50
     liquidity
    0.50
    aarrggbb
    0.49
     presence
    0.48
     Assets
    0.45
    vency
    0.45
     inventory
    0.45
    principalColumn
    0.44
     Antara
    0.44
    Activations Density 0.314%

    No Known Activations