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-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28396
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal contracts and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.63
    ⓧ
    -0.56
    writeFieldEnd
    -0.56
    сшта
    -0.54
    itability
    -0.54
    MLLoader
    -0.54
     popula
    -0.52
     doGet
    -0.51
     sugges
    -0.51
    erol
    -0.51
    POSITIVE LOGITS
     contracts
    1.29
     contract
    1.27
     Contracts
    1.12
     Contract
    1.10
     agreements
    1.09
    contract
    1.09
     contrato
    1.05
    contracts
    1.04
     contractual
    1.01
    Contract
    1.00
    Activations Density 0.556%

    No Known Activations