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

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 12596
    Prev
    Next
    INDEX
    Explanations

    concepts related to choice and autonomy in personal beliefs

    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
    PLOS
    -0.44
    ſen
    -0.37
     qualific
    -0.37
     garg
    -0.36
    hobia
    -0.36
     snel
    -0.36
     semp
    -0.35
     remis
    -0.35
     propósito
    -0.35
     visitó
    -0.35
    POSITIVE LOGITS
     autonomy
    1.12
     independently
    1.05
     самостоятельно
    1.02
    自主
    1.00
     own
    0.99
    自分で
    0.98
     самостоя
    0.98
     autonom
    0.94
     autonomous
    0.94
     samodziel
    0.93
    Activations Density 0.563%

    No Known Activations