© 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. 3-GEMMASCOPE-RES-16K
    6. 10807
    Prev
    Next
    INDEX
    Explanations

    references to mail and mailing practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.88
    ueux
    -0.77
    PHONY
    -0.68
     autorytatywna
    -0.67
     Clarkson
    -0.67
     betweenstory
    -0.66
    nextElement
    -0.65
    rédients
    -0.65
    lernen
    -0.63
    arakhand
    -0.63
    POSITIVE LOGITS
     mail
    3.16
     Mail
    3.12
     MAIL
    3.02
    Mail
    2.93
    mail
    2.84
    MAIL
    2.69
     mails
    2.39
    mails
    2.02
     mailed
    1.91
    Mails
    1.81
    Activations Density 0.047%

    No Known Activations