© 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. 6938
    Prev
    Next
    INDEX
    Explanations

    terms related to commissions and their configurations in a financial context

    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
     kapas
    -0.34
    bindingNavigator
    -0.33
    rapid
    -0.32
     Rapid
    -0.31
     混
    -0.30
     jewelry
    -0.30
     zel
    -0.30
     Extreme
    -0.30
     island
    -0.30
     pake
    -0.29
    POSITIVE LOGITS
    writeField
    0.61
    +#+#
    0.59
     мәкал
    0.59
     royalties
    0.58
     pleaſure
    0.57
     незавершена
    0.56
     profits
    0.55
     regalías
    0.54
    $_['
    0.53
     profit
    0.52
    Activations Density 0.307%

    No Known Activations