© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2116
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the concept of "scratching."

    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
    enterOuterAlt
    -0.72
    didSet
    -0.71
     events
    -0.66
    bindet
    -0.65
     efficiency
    -0.64
     Manuela
    -0.64
    forName
    -0.62
     SOP
    -0.62
    WebControls
    -0.61
     eventos
    -0.61
    POSITIVE LOGITS
     scratch
    3.50
     Scratch
    3.16
    Scratch
    2.97
    scratch
    2.92
     scratching
    2.74
     scratches
    2.70
     scratched
    2.68
     scrat
    2.19
     SCR
    1.48
     scrape
    1.46
    Activations Density 0.078%

    No Known Activations