© 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. 20-GEMMASCOPE-RES-16K
    11. 3487
    Prev
    Next
    INDEX
    Explanations

    the beginning and end of new content or sections in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    time or sequence

    np_acts-logits-general · gemini-2.0-flash

    sequence progression soon later

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -1.14
     Normdatei
    -0.94
    脚注の使い方
    -0.93
    __":
    -0.91
    */;
    -0.91
     pinulongan
    -0.91
    клопе
    -0.91
    出版年
    -0.91
     AssemblyCulture
    -0.90
    Hentet
    -0.88
    POSITIVE LOGITS
     soon
    0.74
    Later
    0.73
     Later
    0.68
    Chapter
    0.68
     Chapter
    0.68
     later
    0.67
    later
    0.66
    ***
    0.66
    Soon
    0.64
     Soon
    0.63
    Activations Density 0.196%

    No Known Activations