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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 5725
    Prev
    Next
    INDEX
    Explanations

    various forms of curly braces and parentheses, typically used to indicate the beginning and end of blocks or structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    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
    -1.08
     فريبيس
    -1.06
     becauſe
    -1.04
     poffible
    -1.00
     myſelf
    -0.99
     pleaſure
    -0.97
     ſeveral
    -0.94
     reaſon
    -0.94
     Reſ
    -0.93
     Eſ
    -0.93
    POSITIVE LOGITS
    ({
    0.84
    ={{
    0.84
    ([
    0.83
     {{
    0.73
    ({"
    0.67
     Pag
    0.63
    Pag
    0.62
    (['
    0.61
     ([
    0.60
    (["
    0.60
    Activations Density 0.176%

    No Known Activations