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. 4149
    Prev
    Next
    INDEX
    Explanations

    code snippets involving layout components in Java or XML

    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
    StructEnd
    -0.71
    AutoScale
    -0.63
    cshtml
    -0.58
    Vorte
    -0.58
    #![
    -0.57
     PAIR
    -0.57
    gameserver
    -0.57
    DIPSETTING
    -0.56
     Italijanski
    -0.56
    tira
    -0.54
    POSITIVE LOGITS
    jPanel
    2.80
     jPanel
    2.24
    JPanel
    1.22
    groupBox
    1.18
     groupBox
    1.06
     JPanel
    0.99
    tableLayoutPanel
    0.92
    jScrollPane
    0.92
     jButton
    0.88
    --}}
    0.87
    Activations Density 0.017%

    No Known Activations