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. 90084
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematics and its applications

    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
     IBOutlet
    -0.61
    omitempty
    -0.56
    $_['
    -0.47
    parsedMessage
    -0.47
    stig
    -0.46
    ftagPool
    -0.45
    bringer
    -0.45
     olev
    -0.45
     createSprite
    -0.45
     Grip
    -0.44
    POSITIVE LOGITS
     mathematics
    1.10
     Mathematics
    1.05
    Mathematics
    0.95
     mathematical
    0.92
     Mathematical
    0.91
    mathematics
    0.91
     mathematician
    0.89
     MATHEMATICS
    0.89
     math
    0.86
     Matem
    0.85
    Activations Density 0.008%

    No Known Activations