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

    Neuronpedia

    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. 21-GEMMASCOPE-RES-16K
    11. 16288
    Prev
    Next
    INDEX
    Explanations

    the word "down" in various contexts, often indicating direction or a decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieß
    -0.61
     Erwä
    -0.59
     laſſen
    -0.59
     wußte
    -0.52
     zoude
    -0.52
     ſeinen
    -0.52
     orejas
    -0.52
     dieſer
    -0.51
     sạn
    -0.50
     müſſen
    -0.49
    POSITIVE LOGITS
     down
    1.31
     Down
    1.30
    Down
    1.21
     DOWN
    1.20
    down
    1.13
    DOWN
    1.08
     downs
    0.96
     Downing
    0.95
    downs
    0.88
     Downs
    0.81
    Activations Density 0.090%

    No Known Activations