© 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. 13685
    Prev
    Next
    INDEX
    Explanations

    events related to gatherings or celebrations

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

    Events, festivals, or gatherings

    np_acts-logits-general · gemini-2.0-flash

    parties and events

    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
     فريبيس
    -0.77
     estekak
    -0.71
    addContainerGap
    -0.65
     ब्रेकडाउन
    -0.60
     odkazy
    -0.58
     funerals
    -0.55
    PickerController
    -0.55
     holidays
    -0.54
     Weihnachten
    -0.53
     Startseite
    -0.53
    POSITIVE LOGITS
     fun
    0.63
    GEBURTSDATUM
    0.60
     DJ
    0.58
     rides
    0.58
     الحره
    0.56
     kids
    0.56
     food
    0.55
     free
    0.55
    Oise
    0.54
     música
    0.54
    Activations Density 0.096%

    No Known Activations