© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9866
    Prev
    Next
    INDEX
    Explanations

    references to famous individuals or notable contributions in the music and entertainment industry

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

    rappers and rap music

    np_acts-logits-general · gemini-2.0-flash

    rap music and rappers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.59
    AccessorTable
    -0.57
    FieldNumber
    -0.55
     TestBed
    -0.54
     riduzione
    -0.54
     regardé
    -0.54
    protoimpl
    -0.52
    izante
    -0.52
    шеб
    -0.50
    gwt
    -0.50
    POSITIVE LOGITS
     rap
    1.18
     rapping
    1.14
     raps
    1.11
     rappers
    1.09
     rhymes
    1.03
     rapper
    1.01
     Rap
    0.91
     rhyme
    0.90
    Rap
    0.87
     hip
    0.86
    Activations Density 0.122%

    No Known Activations