© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2692
    Prev
    Next
    INDEX
    Explanations

    instances of the word "down" and related phrases indicating downward trends or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "down" followed by various prepositions

    np_acts-logits-general · gemini-2.0-flash

    down and phrases like down-regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %)$
    -0.51
     roleId
    -0.50
     laſſen
    -0.48
     hereof
    -0.48
     orejas
    -0.48
     wuß
    -0.47
     dieß
    -0.47
    ceus
    -0.47
     Erwä
    -0.46
     szk
    -0.45
    POSITIVE LOGITS
     down
    2.20
     Down
    2.09
    Down
    2.02
    down
    1.94
     DOWN
    1.91
    DOWN
    1.66
     downs
    1.57
    downs
    1.51
    ダウン
    1.40
     Downs
    1.37
    Activations Density 0.138%

    No Known Activations