© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11674
    Prev
    Next
    INDEX
    Explanations

    references to DJs and music-related terms

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

    DJs and music artists

    np_acts-logits-general · gemini-2.0-flash

    disc jockey mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.50
    protoc
    -0.46
    wikidata
    -0.44
     krok
    -0.44
    NUMX
    -0.43
     buckling
    -0.43
     buckle
    -0.42
    колеп
    -0.42
    poca
    -0.41
     schla
    -0.41
    POSITIVE LOGITS
     DJ
    1.58
     dj
    1.41
    DJ
    1.38
     DJs
    1.35
    dj
    1.21
     Dj
    1.20
    Dj
    1.09
     dee
    0.82
     mixes
    0.72
     mix
    0.65
    Activations Density 0.113%

    No Known Activations