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. 18-GEMMASCOPE-RES-16K
    6. 10272
    Prev
    Next
    INDEX
    Explanations

    legal requirements and standards for proving claims or arguments in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.69
     فريبيس
    -0.66
     насељу
    -0.63
    parsedMessage
    -0.61
     Paglinawan
    -0.60
    addCriterion
    -0.59
    /*
    -0.59
    脚注の使い方
    -0.59
    twimg
    -0.58
    SharedDtor
    -0.57
    POSITIVE LOGITS
    一是
    1.09
     firstly
    1.08
    :
    0.99
     Firstly
    0.95
    ①
    0.94
    :(
    0.89
    )
    0.88
     either
    0.85
    :")
    0.84
    :(
    0.82
    Activations Density 0.820%

    No Known Activations