© 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. 12204
    Prev
    Next
    INDEX
    Explanations

    variations of the word "fast."

    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
     Momente
    -0.41
     divulgação
    -0.41
     realização
    -0.40
     darunter
    -0.40
    jména
    -0.39
     ocasião
    -0.39
     Bedarf
    -0.39
    middels
    -0.38
     reunião
    -0.38
    cessite
    -0.38
    POSITIVE LOGITS
     Fast
    1.13
    Fast
    1.08
     fast
    1.01
    fast
    0.96
     FAST
    0.93
    FAST
    0.84
     paced
    0.71
     faſt
    0.69
     Fas
    0.69
    Fas
    0.69
    Activations Density 0.099%

    No Known Activations