© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12432
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers related to communication or forwarding messages

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

    Email-related tokens

    np_acts-logits-general · gemini-2.0-flash

    email addresses and communication metadata

    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
     surla
    -0.68
     ब्रेकडाउन
    -0.67
    Cyfarwyddwr
    -0.62
    EndContext
    -0.59
     OFDb
    -0.59
     autorytatywna
    -0.57
    enterOuterAlt
    -0.56
    UrlResolution
    -0.55
    Życiorys
    -0.53
    出版年
    -0.51
    POSITIVE LOGITS
    mailto
    0.46
     email
    0.45
    email
    0.41
    Email
    0.38
     VIDEOTAPE
    0.38
    邮件
    0.37
     courriel
    0.36
    mail
    0.36
     secundarios
    0.35
    lastIndex
    0.35
    Activations Density 0.339%

    No Known Activations