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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 12883
    Prev
    Next
    INDEX
    Explanations

    characteristics and attributes related to structure and organization in programming or data handling contexts

    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
    adaptiveStyles
    -0.99
     Drapeau
    -0.85
     utafitiHapana
    -0.84
    出版年
    -0.80
    Datuak
    -0.79
    ReusableCell
    -0.77
    verifyException
    -0.75
    Identyfik
    -0.73
    transQ
    -0.72
     Мексичка
    -0.71
    POSITIVE LOGITS
    dotenv
    0.63
    ollectionView
    0.59
    |()
    0.59
    ruptedException
    0.55
    <>();
    0.53
    npos
    0.53
    innerHeight
    0.52
    chtenstein
    0.51
    ENDIAN
    0.49
     Se
    0.49
    Activations Density 0.070%

    No Known Activations