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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1608
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and periods in technical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pay
    -0.50
     بيها
    -0.49
    ladiator
    -0.48
    ScopeManager
    -0.47
    ESSIONAL
    -0.47
    ellee
    -0.46
    PMailer
    -0.45
     mengen
    -0.44
    geslacht
    -0.44
     min
    -0.44
    POSITIVE LOGITS
    txt
    0.87
     насељу
    0.75
     SEDS
    0.72
     txt
    0.71
     Italijanski
    0.69
     TXT
    0.68
     sumpay
    0.67
    EDEFAULT
    0.62
     okuyayım
    0.61
    ########.
    0.60
    Activations Density 0.194%

    No Known Activations