© 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. 50
    Prev
    Next
    INDEX
    Explanations

    references to the word "created" in various contexts

    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
    verwijspagina
    -0.78
    multicolumn
    -0.72
    chtigkeit
    -0.71
    issauga
    -0.71
     Bep
    -0.69
     Cip
    -0.69
    awarkan
    -0.68
    commentId
    -0.68
     Spi
    -0.68
     Estelle
    -0.67
    POSITIVE LOGITS
    created
    1.27
    Created
    1.15
     Created
    1.14
     created
    1.11
     CREATED
    1.10
    CREATED
    0.98
     produced
    0.87
    Produced
    0.87
     créé
    0.86
     Produced
    0.84
    Activations Density 0.267%

    No Known Activations