© 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. 17-GEMMASCOPE-RES-16K
    6. 13811
    Prev
    Next
    INDEX
    Explanations

    references to user engagement and content popularity in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atser
    -0.43
    orcid
    -0.43
     AlertDialog
    -0.42
     appelez
    -0.41
    Przypisy
    -0.41
     SqlConnection
    -0.41
    навли
    -0.39
    ื่อ
    -0.38
     OpenStreetMap
    -0.38
    дмила
    -0.38
    POSITIVE LOGITS
     trending
    1.07
     Trending
    0.91
    trending
    0.89
     top
    0.89
    Top
    0.86
     Top
    0.86
    popular
    0.85
    Popular
    0.83
     recommendation
    0.81
    Trending
    0.80
    Activations Density 0.258%

    No Known Activations