© 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. 33-GEMMASCOPE-RES-16K
    11. 5570
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recent
    -0.84
     currently
    -0.84
     actuellement
    -0.77
     derzeit
    -0.76
     lately
    -0.73
     attualmente
    -0.72
     recently
    -0.71
     obecnie
    -0.71
     Currently
    -0.70
     senaste
    -0.69
    POSITIVE LOGITS
     damals
    1.08
     damal
    1.02
    当時の
    1.01
    当时的
    0.94
    当時は
    0.94
    当時
    0.90
    當時
    0.90
     damaligen
    0.88
     Yugoslavia
    0.84
     postwar
    0.83
    Activations Density 1.354%

    No Known Activations