© 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. 21-GEMMASCOPE-RES-16K
    6. 15939
    Prev
    Next
    INDEX
    Explanations

    key terms related to the regulation and management of online content and information flow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyVersion
    -0.67
    antası
    -0.58
    مشخصات
    -0.54
     BoxFit
    -0.54
     Viene
    -0.53
     inlay
    -0.50
    ttino
    -0.49
     Himo
    -0.48
    marshaller
    -0.48
    BorderLayout
    -0.48
    POSITIVE LOGITS
     Facebook
    1.52
     Twitter
    1.50
     social
    1.36
     Instagram
    1.36
    Facebook
    1.30
     online
    1.30
     internet
    1.26
    Twitter
    1.26
     Internet
    1.25
     twitter
    1.20
    Activations Density 0.483%

    No Known Activations