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. 33-GEMMASCOPE-RES-131K
    6. 65877
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced theoretical physics concepts, particularly those dealing with the Standard Model and its extensions

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Imaginary
    -0.40
    Amicalement
    -0.36
     שוליים
    -0.35
    deer
    -0.35
     pousser
    -0.35
     nghi
    -0.35
     cellpadding
    -0.34
    bearded
    -0.34
     Bertram
    -0.34
     mesh
    -0.33
    POSITIVE LOGITS
    RegressionTest
    0.63
     Planck
    0.60
    CodeAttribute
    0.52
     TeV
    0.52
    IsContent
    0.52
     compac
    0.50
    MemoryWarning
    0.48
    parsedMessage
    0.48
    AnchorStyles
    0.48
     NSCoder
    0.48
    Activations Density 0.072%

    No Known Activations