© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2391
    Prev
    Next
    INDEX
    Explanations

    the beginning of new paragraphs or sections in the text

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

    obituary, funeral, condolences

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    bruk
    -0.49
    шна
    -0.48
     zain
    -0.46
     pitted
    -0.46
     primer
    -0.46
     jspb
    -0.46
    المشاركات
    -0.46
    マスター
    -0.45
    zące
    -0.44
    Downloaded
    -0.43
    POSITIVE LOGITS
     obituary
    1.16
     mourners
    1.10
     funeral
    1.06
     cremation
    0.99
     OBITUARY
    0.97
     Funeral
    0.96
    Obituary
    0.96
     Obituary
    0.95
     Trauer
    0.95
     Condol
    0.94
    Activations Density 0.009%

    No Known Activations