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. 122722
    Prev
    Next
    INDEX
    Explanations

    concepts related to gravity and motion dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    cshtml
    -0.46
    
    -0.46
    WebServlet
    -0.45
    Bibliograf
    -0.43
     yym
    -0.41
     disambiguazione
    -0.41
     Employ
    -0.41
     iprot
    -0.40
    Capítulo
    -0.39
     eigenvectors
    -0.39
    POSITIVE LOGITS
    cessite
    0.40
     detalj
    0.39
    berdayakan
    0.39
    alakip
    0.39
     acceleration
    0.36
     reç
    0.35
    eluarkan
    0.34
    borderFill
    0.34
     đương
    0.33
    neider
    0.33
    Activations Density 0.192%

    No Known Activations