© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 12315
    Prev
    Next
    INDEX
    Explanations

    concepts or references related to the idea of being "beyond" or exceeding a certain limit or expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Schneider
    -0.56
     huawei
    -0.55
     helst
    -0.54
    شاركة
    -0.54
     चीज़ों
    -0.52
     وتسجيلات
    -0.52
    RTLR
    -0.52
    openConnection
    -0.50
    سكري
    -0.49
    enterOuterAlt
    -0.48
    POSITIVE LOGITS
    YOND
    1.52
     beyond
    1.43
     Beyond
    1.39
    beyond
    1.38
     BEYOND
    1.38
    Beyond
    1.35
    delà
    0.99
     Bez
    0.84
     borders
    0.83
    */;
    0.81
    Activations Density 0.065%

    No Known Activations