© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    terms related to public events or gatherings, particularly those involving memorials or celebrations of life

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

    Preceding words before technical or numerical content

    np_acts-logits-general · gemini-2.0-flash

    funeral, obituary, cremation

    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
     Agora
    -0.57
    inari
    -0.55
    viste
    -0.54
     agora
    -0.53
    eighth
    -0.52
     zugesch
    -0.52
    mListener
    -0.52
    ようになりました
    -0.52
    zili
    -0.52
    zzar
    -0.51
    POSITIVE LOGITS
     funeral
    0.71
     Funeral
    0.69
    DockStyle
    0.67
    出版年
    0.67
    Datuak
    0.60
     obituary
    0.59
     Cremation
    0.57
    новниш
    0.56
     snippetHide
    0.55
    funeral
    0.54
    Activations Density 0.008%

    No Known Activations