Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6809
    Prev
    Next
    INDEX
    Explanations

    information related to burials and graves

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.66
     <=",
    -0.65
     CURIAM
    -0.63
    Geplaatst
    -0.52
    الحياه
    -0.52
    Gambas
    -0.51
     lọc
    -0.50
     éto
    -0.49
    ódnica
    -0.47
    下载附件
    -0.47
    POSITIVE LOGITS
     burial
    1.83
     funeral
    1.59
     buried
    1.57
     Burial
    1.54
     coffin
    1.50
     bury
    1.46
     graves
    1.45
     burials
    1.44
     corpse
    1.42
     cremation
    1.41
    Activations Density 0.270%

    No Known Activations