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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 14860
    Prev
    Next
    INDEX
    Explanations

    references to email protocols and configuration details

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

    Email or mail-related text

    np_acts-logits-general · gemini-2.0-flash

    send mail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegistryLite
    -0.88
     onCreateView
    -0.87
    ValueStyle
    -0.77
    :✨
    -0.75
     مرئيه
    -0.72
    UnknownFields
    -0.71
     StatefulWidget
    -0.70
    出版年
    -0.69
     становника
    -0.69
    rungsseite
    -0.69
    POSITIVE LOGITS
     email
    1.14
     mail
    1.11
     Mail
    1.07
     Email
    1.06
     emails
    1.04
    smtp
    1.03
     MAIL
    1.03
    mail
    1.02
     Emails
    1.02
     SMTP
    1.00
    Activations Density 0.268%

    No Known Activations