© 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. 36-GEMMASCOPE-RES-16K
    11. 10568
    Prev
    Next
    INDEX
    Explanations

    comparative terms and adverbs that indicate degrees or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     très
    -0.60
     muy
    -0.60
    DockStyle
    -0.60
    Très
    -0.59
     muito
    -0.59
     mucho
    -0.57
     insanely
    -0.57
     funnier
    -0.56
     smartest
    -0.53
     beaucoup
    -0.53
    POSITIVE LOGITS
     acute
    0.50
     representative
    0.49
     widespread
    0.48
     pervasive
    0.45
     ſever
    0.43
     frequent
    0.42
     robust
    0.42
     closely
    0.42
     pronounced
    0.42
    まま
    0.42
    Activations Density 0.599%

    No Known Activations