© 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. 18-GEMMASCOPE-RES-16K
    6. 9378
    Prev
    Next
    INDEX
    Explanations

    instances of interpersonal conflict and emotional reactions in relationships

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

    "Soap" or "soap opera" related words

    np_acts-logits-general · gemini-2.0-flash

    soap opera drama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\..\
    -0.63
    ArgsConstructor
    -0.51
    HtmlAttribute
    -0.48
     pó
    -0.46
     StatelessWidget
    -0.46
     nonUne
    -0.44
     princípios
    -0.43
     parfaitement
    -0.42
    BagConstraints
    -0.42
     hini
    -0.42
    POSITIVE LOGITS
     soap
    1.23
     Soap
    1.06
    soap
    1.03
     soaps
    1.02
    Soap
    0.93
     soapy
    0.91
    Enders
    0.76
     daytime
    0.75
     storyline
    0.72
     teleno
    0.72
    Activations Density 0.063%

    No Known Activations