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. 4-GEMMASCOPE-RES-16K
    6. 668
    Prev
    Next
    INDEX
    Explanations

    titles or names of individuals, particularly in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.62
    ंदीखरीदारी
    -0.56
    +#+#
    -0.54
     Paglinawan
    -0.53
     cops
    -0.53
     animada
    -0.49
    futbolista
    -0.48
     suerte
    -0.47
    __((
    -0.47
     attested
    -0.47
    POSITIVE LOGITS
     Herrn
    0.83
     Herr
    0.77
     senhor
    0.71
    sieurs
    0.70
     Mr
    0.70
     Messrs
    0.69
     Senhor
    0.69
     señor
    0.69
     Gentlemen
    0.67
    Monsieur
    0.67
    Activations Density 0.513%

    No Known Activations