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. 29302
    Prev
    Next
    INDEX
    Explanations

    syllables or terms related to various forms of the word "synergy" and their associations, particularly in a scientific or medical context

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

    words beginning with 'sy'

    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
    fcntl
    -0.56
    ../../
    -0.54
     hendak
    -0.45
    담
    -0.44
     préalable
    -0.44
    argout
    -0.43
    PickerController
    -0.43
     περισσότε
    -0.43
    Slf
    -0.42
     المعيارى
    -0.42
    POSITIVE LOGITS
     Sy
    0.89
    Sy
    0.86
     ſy
    0.82
     Sycamore
    0.81
     SY
    0.79
     Synergy
    0.75
     Synt
    0.73
     Sykes
    0.73
     Syria
    0.69
     sy
    0.69
    Activations Density 0.009%

    No Known Activations