© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6909
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and measurement in health studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.37
    Tan
    -0.35
    AnimationsModule
    -0.34
     Templeton
    -0.32
    iecie
    -0.32
     PagesJaunes
    -0.32
    Kjelder
    -0.31
     Ти
    -0.31
    Tenn
    -0.31
    wpi
    -0.31
    POSITIVE LOGITS
     Tra
    2.67
     tra
    2.53
    Tra
    2.48
    tra
    2.36
     TRA
    2.22
     Тра
    2.13
    トラ
    2.09
     trac
    2.06
     тра
    2.05
     Tracy
    2.02
    Activations Density 2.421%

    No Known Activations