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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3538
    Prev
    Next
    INDEX
    Explanations

    references to email functions and SMTP configurations

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

    "mail" and email-related terms

    np_acts-logits-general · gemini-2.0-flash

    mail delivery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Signalez
    -0.55
    gucig
    -0.55
     Herrschaft
    -0.46
    ValueGenerated
    -0.45
    cellona
    -0.43
     castelo
    -0.42
    براير
    -0.41
     flèche
    -0.41
    Дереккөздер
    -0.40
     culturali
    -0.40
    POSITIVE LOGITS
    PMailer
    1.27
     smtplib
    1.06
     mail
    0.78
    mail
    0.77
    Mail
    0.73
     Mail
    0.72
     SMTP
    0.68
     smtp
    0.63
     Gmail
    0.63
    mailer
    0.63
    Activations Density 0.227%

    No Known Activations