© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 16038
    Prev
    Next
    INDEX
    Explanations

    conversations or arguments about belief systems and their impact on perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     additional
    -0.36
     yardımcı
    -0.35
     langen
    -0.34
     дополнительных
    -0.34
     Haupt
    -0.32
     szuka
    -0.32
     hacerlo
    -0.32
     geçi
    -0.31
     açık
    -0.30
     Ewig
    -0.29
    POSITIVE LOGITS
     automobiles
    1.04
     airplanes
    1.02
     aeroplane
    0.98
     eiffel
    0.96
     automobile
    0.96
     baseball
    0.94
     ſind
    0.94
     airplane
    0.93
     football
    0.93
     Shakspeare
    0.93
    Activations Density 0.985%

    No Known Activations