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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 90559
    Prev
    Next
    INDEX
    Explanations

    terms related to different times of day, particularly focusing on meal times and other daily activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    daytime, nighttime, and other times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     gouver
    -0.55
     Administrativna
    -0.53
     ponts
    -0.50
     étrangère
    -0.50
     credere
    -0.49
     vuestros
    -0.48
     ģ
    -0.47
     cappuccio
    -0.47
     mijne
    -0.47
     Volkes
    -0.46
    POSITIVE LOGITS
     nighttime
    1.07
     daytime
    1.03
     lunchtime
    0.99
    atime
    0.99
     playtime
    0.97
    time
    0.94
     wartime
    0.89
     endTime
    0.89
    TIME
    0.85
    Time
    0.81
    Activations Density 0.011%

    No Known Activations