© 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. 34-GEMMASCOPE-RES-16K
    11. 10763
    Prev
    Next
    INDEX
    Explanations

    concerns related to email management and data retrieval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.56
     CanadaChoose
    -0.53
    pulseira
    -0.50
    .*")]
    -0.50
     @"/
    -0.49
     nationaux
    -0.48
     nahilalakip
    -0.47
     ब्रेकडाउन
    -0.45
    miendo
    -0.45
    complexContent
    -0.44
    POSITIVE LOGITS
     Mail
    1.13
     mail
    1.10
     mailbox
    1.02
    mail
    0.98
    Mail
    0.98
     MAIL
    0.96
    MAIL
    0.89
     Gmail
    0.82
     SMTP
    0.81
     mails
    0.80
    Activations Density 0.400%

    No Known Activations