© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15142
    Prev
    Next
    INDEX
    Explanations

    content focused on providing educational and informative resources for businesses

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

    relating to content creation/management

    np_acts-logits-general · gemini-2.0-flash

    producing long-form content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereof
    -0.57
    Jeografia
    -0.56
     cowards
    -0.54
     cherchés
    -0.54
    WSGI
    -0.53
    Према
    -0.52
    effet
    -0.52
    EndGlobalSection
    -0.52
     INTERNET
    -0.51
    Internet
    -0.50
    POSITIVE LOGITS
     content
    1.06
     contenido
    0.83
     Content
    0.79
    content
    0.77
     contenu
    0.72
     influencer
    0.71
     CONTENT
    0.71
     contenuti
    0.71
    Content
    0.70
     konten
    0.69
    Activations Density 0.155%

    No Known Activations