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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3566
    Prev
    Next
    INDEX
    Explanations

    references to times of day, specifically mornings and their associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.46
     lentejuelas
    -0.44
     Spass
    -0.43
     serata
    -0.43
    eschou
    -0.42
    ListActivity
    -0.41
     láser
    -0.39
     pozdě
    -0.39
     cuero
    -0.39
    cology
    -0.39
    POSITIVE LOGITS
     morning
    1.67
    morning
    1.52
    Morning
    1.46
     breakfast
    1.45
     MORNING
    1.41
     Morning
    1.39
     mornings
    1.38
    breakfast
    1.36
     Breakfast
    1.34
    Breakfast
    1.31
    Activations Density 0.232%

    No Known Activations