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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6089
    Prev
    Next
    INDEX
    Explanations

    references to the term "par" and its associated variations, indicating a focus on parameters or discussions around "par" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.95
     Roskov
    -0.92
    ")->
    -0.80
    ExecuteReader
    -0.80
    AccessorTable
    -0.79
     jedis
    -0.78
    colage
    -0.76
    ;">
    
    -0.75
     useEffect
    -0.74
    ,))
    -0.74
    POSITIVE LOGITS
    par
    3.21
     par
    3.14
    Par
    3.10
     Par
    3.08
     PAR
    2.82
    PAR
    2.66
    Pars
    1.73
     Parr
    1.70
     pars
    1.69
     Parac
    1.66
    Activations Density 0.058%

    No Known Activations