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. 12-GEMMASCOPE-RES-16K
    6. 4339
    Prev
    Next
    INDEX
    Explanations

    the term 'par' in various contexts, often related to parsing, parameters, and specific terminologies in fields like programming or medical discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringBootTest
    -1.05
     متعلقه
    -0.95
    
    -0.89
    jsii
    -0.88
    Sucesor
    -0.88
     Roskov
    -0.87
    awtextra
    -0.87
     &___
    -0.84
    ьаж
    -0.84
    ApplicationTests
    -0.82
    POSITIVE LOGITS
     PAR
    1.48
    par
    1.48
    PAR
    1.37
    Par
    1.34
     Par
    1.28
    Pars
    1.27
     Parrish
    1.25
     Parr
    1.20
     pars
    1.16
     par
    1.15
    Activations Density 0.108%

    No Known Activations