Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9495
    Prev
    Next
    INDEX
    Explanations

    instances of the word "prepared."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.65
    jTable
    -0.60
    édrale
    -0.59
    BeforeClass
    -0.54
     امريكا
    -0.53
    richting
    -0.52
     пузы
    -0.52
    QMessageBox
    -0.51
     dibutuhkan
    -0.51
     necessárias
    -0.50
    POSITIVE LOGITS
     prepared
    2.87
    prepared
    2.53
     Prepared
    2.45
    Prepared
    1.95
    PARED
    1.33
     préparé
    1.25
     preparado
    1.21
     unprepared
    1.17
     preparada
    1.16
     preparados
    1.02
    Activations Density 0.160%

    No Known Activations