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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113876
    Prev
    Next
    INDEX
    Explanations

    phrases related to time periods and durations

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

    periods in days

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ComVisible
    -0.51
     mancher
    -0.38
     normalidad
    -0.35
     colorear
    -0.34
    accompag
    -0.34
     pomeriggio
    -0.33
     morning
    -0.33
     cooperación
    -0.32
     descansar
    -0.32
     repuesto
    -0.32
    POSITIVE LOGITS
     calend
    0.70
    orianCalendar
    0.65
    Days
    0.63
     Days
    0.59
    readystatechange
    0.59
     DAYS
    0.57
    DAYS
    0.56
    جلس
    0.56
     calendario
    0.56
     calendar
    0.56
    Activations Density 0.020%

    No Known Activations