© 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. 23-GEMMASCOPE-RES-16K
    6. 5216
    Prev
    Next
    INDEX
    Explanations

    references to events or characteristics related to people in the context of entertainment and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vicina
    -0.60
     nôtre
    -0.59
     wikipagina
    -0.59
     Carriers
    -0.58
    IVEREF
    -0.57
     ktorí
    -0.57
     bitches
    -0.56
    Gambas
    -0.55
     fools
    -0.55
     katze
    -0.54
    POSITIVE LOGITS
     former
    1.34
    Former
    1.08
    former
    1.04
     Former
    1.02
     ex
    0.93
     veteran
    0.89
     ehemalige
    0.85
     ehemaligen
    0.80
     seasoned
    0.77
    localctx
    0.74
    Activations Density 0.145%

    No Known Activations