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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73675
    Prev
    Next
    INDEX
    Explanations

    the start of sections or paragraphs in the text

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

    The token "bos" appears at the beginning of documents, serving as a marker that indicates the start of a new text in a corpus or dataset.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     незавершена
    -0.90
     estekak
    -0.88
    tagHelperRunner
    -0.87
     فريبيس
    -0.87
    rungsseite
    -0.81
    IsContent
    -0.77
    ViewFeatures
    -0.75
    RenderAtEndOf
    -0.73
    parsedMessage
    -0.72
     CreateTagHelper
    -0.71
    POSITIVE LOGITS
    gesellschaft
    0.35
    case
    0.34
    set
    0.33
    lists
    0.33
    zh
    0.32
    Искәрмәләр
    0.31
    6
    0.31
    
    0.31
    kammer
    0.30
     Moscow
    0.29
    Activations Density 0.004%

    No Known Activations