© 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. 20-GEMMASCOPE-RES-16K
    6. 77
    Prev
    Next
    INDEX
    Explanations

    code structures and functions related to email protocols and authentication

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

    email or mail

    np_acts-logits-general · gemini-2.0-flash

    sending email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مرئيه
    -0.98
    :✨
    -0.85
    ंदीखरीदारी
    -0.83
    RegistryLite
    -0.81
    parency
    -0.71
     onCreateView
    -0.66
     autorytatywna
    -0.66
    Халык
    -0.65
    WillAppear
    -0.60
     StatefulWidget
    -0.59
    POSITIVE LOGITS
     email
    1.54
     mail
    1.53
     Mail
    1.50
    mail
    1.45
     Email
    1.43
     MAIL
    1.40
    Mail
    1.40
     emails
    1.38
    Email
    1.36
     mailbox
    1.34
    Activations Density 0.293%

    No Known Activations