© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 13922
    Prev
    Next
    INDEX
    Explanations

    opening and closing tags in a markup or programming language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -1.08
     الرياضيه
    -0.93
     Monfieur
    -0.90
     Efq
    -0.88
    bibfield
    -0.88
    ſelf
    -0.86
     myſelf
    -0.85
    ItemBackground
    -0.83
     وتسجيلات
    -0.82
    NUMX
    -0.81
    POSITIVE LOGITS
    <
    0.71
    <tr>
    0.58
     <
    0.57
    ={<
    0.56
    .
    0.48
    div
    0.48
     do
    0.45
    <table>
    0.45
     [
    0.43
    –
    0.42
    Activations Density 0.078%

    No Known Activations