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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 13893
    Prev
    Next
    INDEX
    Explanations

    references to mail and mailing processes

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

    the word "mail" and related postal delivery concepts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.51
    CppMethod
    -0.41
    Viitteet
    -0.40
     symmetry
    -0.36
    HasAnnotation
    -0.35
    SupportActionBar
    -0.34
    Pautan
    -0.33
    IConfiguration
    -0.33
     augen
    -0.33
    AccessorTable
    -0.33
    POSITIVE LOGITS
     mail
    2.39
     mailed
    2.08
     Mail
    1.93
     postal
    1.91
     mailing
    1.89
     MAIL
    1.89
     mails
    1.85
    Mail
    1.84
    mail
    1.77
    MAIL
    1.69
    Activations Density 0.499%

    No Known Activations