© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11751
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of "down" or "downward."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     ويكيميديا
    -0.56
     zoude
    -0.54
    Gweler
    -0.54
    цездатний
    -0.53
    AccessorTable
    -0.53
     laſſen
    -0.52
    rlpool
    -0.51
     kaarangay
    -0.50
    ьаж
    -0.50
     dieſer
    -0.49
    POSITIVE LOGITS
    down
    1.52
    Down
    1.36
     Down
    1.27
     down
    1.20
    DOWN
    1.17
     DOWN
    1.12
    downs
    0.98
     downs
    0.94
    ダウン
    0.92
     Downs
    0.88
    Activations Density 0.271%

    No Known Activations