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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11126
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a"

    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
     purpoſe
    -0.62
    nome
    -0.60
     sels
    -0.60
     يتيمه
    -0.59
     expli
    -0.59
     Conſ
    -0.59
     Tér
    -0.58
     alis
    -0.58
    bootstrapcdn
    -0.57
    ‌های
    -0.56
    POSITIVE LOGITS
     brancas
    0.75
    __':
    0.72
    parsedMessage
    0.71
     rendus
    0.71
     vermelhas
    0.70
    ьаж
    0.69
     clínicos
    0.69
     tjen
    0.68
     desorption
    0.67
    bitField
    0.66
    Activations Density 0.186%

    No Known Activations