© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 609
    Prev
    Next
    INDEX
    Explanations

    references to time periods, particularly focusing on days of the week and scheduling

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

    Days and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.57
    Sunday
    -0.54
    sunday
    -0.53
     SUNDAY
    -0.50
     Sunday
    -0.50
     Saturdays
    -0.49
     domingos
    -0.48
    VersionUID
    -0.47
     sunday
    -0.47
    SUNDAY
    -0.47
    POSITIVE LOGITS
     nightly
    0.50
     ContentValues
    0.48
    insertion
    0.47
     night
    0.47
    الحياه
    0.46
    HandlerContext
    0.46
     المعيارى
    0.46
    yntaxException
    0.46
     insertion
    0.45
    night
    0.45
    Activations Density 0.012%

    No Known Activations