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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 438
    Prev
    Next
    INDEX
    Explanations

    occurrences of time-related phrases and expressions

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

    Times of day, often with AM or night

    np_acts-logits-general · gemini-2.0-flash

    times of night and early morning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rrggbb
    -0.65
     propOrder
    -0.63
    ViewImports
    -0.63
    WithIOException
    -0.63
    onViewCreated
    -0.58
    رشف
    -0.57
    TagMode
    -0.52
    ografija
    -0.50
     समीक्षक
    -0.50
    rungsseite
    -0.49
    POSITIVE LOGITS
     night
    1.05
     midnight
    0.91
     NIGHT
    0.87
    night
    0.86
     Night
    0.86
    Night
    0.85
     nighttime
    0.82
    midnight
    0.80
     nachts
    0.79
     nocturnal
    0.78
    Activations Density 0.166%

    No Known Activations