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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 707
    Prev
    Next
    INDEX
    Explanations

    the word "just" 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 @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Serp
    -0.79
    Eileen
    -0.77
     Beowulf
    -0.75
    hyung
    -0.73
    monger
    -0.73
     Vitae
    -0.71
    falcon
    -0.71
     Dooley
    -0.70
    tableWidget
    -0.69
    ResponseWriter
    -0.69
    POSITIVE LOGITS
     just
    1.60
     JUST
    1.56
     Just
    1.55
    JUST
    1.53
    just
    1.51
    Just
    1.49
     Justine
    1.11
     juste
    1.06
     barely
    1.05
     Justus
    1.00
    Activations Density 0.086%

    No Known Activations