© 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
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9140
    Prev
    Next
    INDEX
    Explanations

    instances of the word "great" and its variations, along with associated adjectives and phrases indicating significance or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Porch
    -0.58
    pholes
    -0.57
    MLLoader
    -0.57
    </tfoot>
    -0.55
     Orchid
    -0.55
     autopilot
    -0.55
     Limb
    -0.55
     queſta
    -0.54
     /\.(
    -0.54
    chauss
    -0.54
    POSITIVE LOGITS
     great
    1.72
    great
    1.71
    Great
    1.54
     Great
    1.52
     GREAT
    1.45
    GREAT
    1.41
    TheGreat
    1.02
    greatest
    0.98
     greatest
    0.98
     greate
    0.93
    Activations Density 0.122%

    No Known Activations