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. 22-GEMMASCOPE-RES-16K
    6. 5797
    Prev
    Next
    INDEX
    Explanations

    punctuation and question marks, indicating inquiry or confusion

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

    Follows questions or quotations

    np_acts-logits-general · gemini-2.0-flash

    well, or similar introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.67
    ArgumentParser
    -0.58
    }]{
    -0.53
    Datuak
    -0.52
    queta
    -0.50
    ]+"
    -0.50
    はじめに
    -0.49
    urlpatterns
    -0.49
     TextAlign
    -0.48
    فایل‌لار
    -0.47
    POSITIVE LOGITS
     well
    3.20
     Well
    2.92
    Well
    2.88
    well
    2.69
     WELL
    2.49
    WELL
    2.29
    wells
    1.67
     bien
    1.64
     wells
    1.63
     Pues
    1.51
    Activations Density 0.246%

    No Known Activations