© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 8217
    Prev
    Next
    INDEX
    Explanations

    complex relationships and comparisons involving health, race, and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maupun
    -0.88
     lẫn
    -0.59
    -,
    -0.50
     &
    -0.49
     či
    -0.49
    -/
    -0.44
     bzw
    -0.44
     \&
    -0.43
     sekä
    -0.42
     ataupun
    -0.42
    POSITIVE LOGITS
     והוא
    1.06
     iar
    0.92
     And
    0.90
    并且
    0.87
     gynhyrchwyd
    0.81
    이고
    0.81
     незавершена
    0.79
    ようで
    0.78
    And
    0.76
     eikä
    0.76
    Activations Density 3.897%

    No Known Activations