© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 1037
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to social media account management, particularly focused on Facebook

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.87
     étoient
    -0.79
    最快更新
    -0.78
    httphttps
    -0.77
    rungsseite
    -0.75
     Komunikasi
    -0.71
     Keuangan
    -0.71
     Réponses
    -0.70
    actéristi
    -0.69
    mption
    -0.68
    POSITIVE LOGITS
     neutral
    0.36
     demon
    0.35
     re
    0.33
     точку
    0.33
     ra
    0.33
     dep
    0.32
    zimmer
    0.31
     perfection
    0.31
     вы
    0.30
    委
    0.30
    Activations Density 0.173%

    No Known Activations