Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 10428
    Prev
    Next
    INDEX
    Explanations

    specific terms related to programming and technical specifications

    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
    حياتها
    -0.71
    ◀
    -0.53
    RegressionTest
    -0.51
     menu
    -0.49
     Menu
    -0.49
    TabLayout
    -0.48
     Mode
    -0.48
    trum
    -0.47
     مرئيه
    -0.47
    Dermott
    -0.47
    POSITIVE LOGITS
     Normdatei
    0.70
     giustizia
    0.67
     antennas
    0.66
    reactstrap
    0.66
    webdriver
    0.64
     navideño
    0.62
    Fra
    0.62
     hugging
    0.62
     hugged
    0.62
     Fra
    0.61
    Activations Density 1.938%

    No Known Activations