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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 13371
    Prev
    Next
    INDEX
    Explanations

    elements related to singing and vocal performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Савезне
    -0.65
    الإنجليزية
    -0.63
    Lịch
    -0.59
    RenderAtEndOf
    -0.57
    minecraftforge
    -0.56
    ритори
    -0.53
    rasil
    -0.52
     neutron
    -0.51
     skateboarding
    -0.50
    ContentAsync
    -0.49
    POSITIVE LOGITS
     singing
    1.73
     singers
    1.51
     sung
    1.51
     sang
    1.49
     Singing
    1.45
     sings
    1.44
    Singing
    1.41
    singing
    1.41
     sing
    1.38
     vocals
    1.32
    Activations Density 0.124%

    No Known Activations