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. 29317
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and dashes

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

    quotation marks and enclosing punctuation

    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
     Meet
    -0.55
    Mayer
    -0.54
    Leary
    -0.53
     Macy
    -0.52
    Meet
    -0.52
    ✔
    -0.51
    UAV
    -0.51
    chargez
    -0.51
    -
    -0.48
    viewDid
    -0.48
    POSITIVE LOGITS
     ''
    0.84
    ('''
    0.73
     ''){
    0.72
    =''
    0.68
     '')
    0.68
    ''''
    0.67
     [''
    0.66
     '',
    0.66
    ''
    0.65
     '';
    0.65
    Activations Density 0.015%

    No Known Activations