© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4692
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "down" and its variations indicating downward movement or decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wußte
    -0.57
     müſſen
    -0.56
     laſſen
    -0.56
     Erwä
    -0.54
     dieß
    -0.54
     ſeinen
    -0.54
     dieſer
    -0.53
     Geiſt
    -0.53
     GenerationType
    -0.52
     fédé
    -0.52
    POSITIVE LOGITS
     down
    1.70
     Down
    1.66
    Down
    1.57
     DOWN
    1.52
    down
    1.48
    DOWN
    1.35
     downs
    1.25
    downs
    1.16
     Downing
    1.13
    ダウン
    1.08
    Activations Density 0.095%

    No Known Activations