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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 39501
    Prev
    Next
    INDEX
    Explanations

    details related to time and its progression or changes

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

    time, duration, past, or future states

    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
    SharedCtor
    -0.71
    GEBURTSDATUM
    -0.58
    contentLoaded
    -0.58
     وتسجيلات
    -0.56
     propOrder
    -0.54
     незавершена
    -0.53
    MLLoader
    -0.51
     miniaturka
    -0.50
     Roskov
    -0.50
     myſelf
    -0.49
    POSITIVE LOGITS
     temporary
    0.39
     temporarily
    0.37
    temporary
    0.36
    currentColor
    0.35
     mã
    0.34
     prominently
    0.34
    tempor
    0.33
     transient
    0.33
    stage
    0.33
    jsonPath
    0.33
    Activations Density 0.103%

    No Known Activations