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. 5-GEMMASCOPE-RES-16K
    6. 12773
    Prev
    Next
    INDEX
    Explanations

    characteristic features of language and culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sno
    -0.56
     ro
    -0.53
    יני
    -0.53
     Duro
    -0.52
    dlo
    -0.50
     文
    -0.50
    Collegamenti
    -0.50
    Altri
    -0.49
     bla
    -0.49
    =”
    -0.49
    POSITIVE LOGITS
     Administrativna
    0.85
     Paglinawan
    0.74
     bezeichneter
    0.73
    Pautan
    0.70
     îna
    0.70
     pitié
    0.68
    epam
    0.67
    ниципа
    0.67
     Chwiliwch
    0.67
     ressemb
    0.66
    Activations Density 0.823%

    No Known Activations