© 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. 4-GEMMASCOPE-RES-16K
    6. 2323
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "change" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bienvenue
    -0.95
     récon
    -0.92
     mijne
    -0.87
    Portale
    -0.85
     hereof
    -0.84
    fifths
    -0.84
     nationaux
    -0.83
     pitié
    -0.83
     urbanos
    -0.82
     réfrig
    -0.81
    POSITIVE LOGITS
     change
    2.14
     Change
    2.00
    Change
    1.93
     CHANGE
    1.91
     changes
    1.85
    change
    1.80
     changing
    1.78
    CHANGE
    1.77
     changed
    1.77
     changer
    1.73
    Activations Density 0.090%

    No Known Activations