Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 91502
    Prev
    Next
    INDEX
    Explanations

    phrases related to contractual terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     watchers
    -0.47
     rabbits
    -0.45
     Rabbit
    -0.45
     Goldsmith
    -0.45
     rabbit
    -0.45
     woodpecker
    -0.44
     bunnies
    -0.43
     miss
    -0.43
     Asheville
    -0.43
     AppColors
    -0.42
    POSITIVE LOGITS
     terms
    0.84
    Terms
    0.83
     Terms
    0.81
    terms
    0.79
     TERMS
    0.74
     conditions
    0.66
    TERMS
    0.66
     términos
    0.63
     Conditions
    0.63
    matchCondition
    0.62
    Activations Density 0.012%

    No Known Activations