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-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 132
    Prev
    Next
    INDEX
    Explanations

    lines of code related to importing packages and libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.34
     weekly
    -0.30
    ante
    -0.28
    headline
    -0.27
    DateTimeField
    -0.27
    assertArray
    -0.27
     Newspaper
    -0.26
     bero
    -0.26
    phane
    -0.25
     statistical
    -0.25
    POSITIVE LOGITS
    httphttps
    0.85
    :✨
    0.74
    SequentialGroup
    0.65
    ⓧ
    0.63
     متعلقه
    0.63
     estekak
    0.62
     تضيفلها
    0.62
     незавершена
    0.61
    UrlResolution
    0.61
     utafitiHapana
    0.60
    Activations Density 0.116%

    No Known Activations