© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3725
    Prev
    Next
    INDEX
    Explanations

    references to soap operas and their attributes

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

    Soap operas and TV series

    np_acts-logits-general · gemini-2.0-flash

    soap opera storylines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.53
     "..\..\..\
    -0.53
    ArgsConstructor
    -0.49
     StatelessWidget
    -0.48
    HtmlAttribute
    -0.46
     impianti
    -0.44
    曖昧さ回避
    -0.43
    AccessException
    -0.41
    Clive
    -0.41
     pó
    -0.41
    POSITIVE LOGITS
     soap
    1.12
     Soap
    1.02
     soaps
    1.00
    Soap
    0.91
    soap
    0.88
     soapy
    0.77
    Enders
    0.73
     storylines
    0.71
     sabun
    0.71
     storyline
    0.71
    Activations Density 0.043%

    No Known Activations