© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2281
    Prev
    Next
    INDEX
    Explanations

    the word "saw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.81
    WEBPACK
    -0.75
     Petersen
    -0.71
     <<<<<<<<<<<<<<
    -0.68
     Morrison
    -0.67
    BindingResult
    -0.67
    +#+#
    -0.67
     dinh
    -0.66
    printStackTrace
    -0.64
    ξη
    -0.63
    POSITIVE LOGITS
    saw
    2.62
     saw
    2.55
    Saw
    2.48
     Saw
    2.47
     SAW
    2.13
     saws
    1.67
    SAW
    1.62
     Sawyer
    1.54
     sawing
    1.48
     faw
    1.17
    Activations Density 0.052%

    No Known Activations