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. 117271
    Prev
    Next
    INDEX
    Explanations

    references to devices and their roles in a system or process

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

    Technical punctuation marks, symbols, and formatting elements in academic or specialized writing, particularly quotation marks, parentheses, numbers in citations, and connecting punctuation.

    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
     виправивши
    -0.75
     '\\;'
    -0.69
    Parcelize
    -0.67
    Diweddarwch
    -0.66
    ErrUnexpectedEOF
    -0.64
     müſſen
    -0.63
     témoig
    -0.63
    تقاوى
    -0.63
    <unused8>
    -0.60
    <unused14>
    -0.60
    POSITIVE LOGITS
    .
    0.34
     $
    0.34
     hati
    0.31
     .
    0.30
    ולוג
    0.30
     onlyOwner
    0.29
    都合
    0.28
    ↵
    0.28
      
    0.27
    sendFile
    0.27
    Activations Density 0.613%

    No Known Activations