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 - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2409
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to transactions and their processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.97
     CreateTagHelper
    -0.91
    揄
    -0.90
     apprécié
    -0.87
     WaitForSeconds
    -0.87
    cipital
    -0.80
     réunis
    -0.80
     Reif
    -0.79
    quelles
    -0.78
     avoient
    -0.76
    POSITIVE LOGITS
     transactions
    1.75
     transaction
    1.70
     Transactions
    1.52
     Transaction
    1.52
    transaction
    1.42
    Transactions
    1.39
    transactions
    1.37
    Transaction
    1.34
     TRANSACTION
    1.24
     transactional
    1.20
    Activations Density 0.052%

    No Known Activations