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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 746
    Prev
    Next
    INDEX
    Explanations

    names of music groups and orchestras

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

    names and details of musical compositions, orchestras, and musical credits.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     OMITBAD
    -0.46
    quilo
    -0.41
    Referințe
    -0.37
     nahilalakip
    -0.37
     OFDb
    -0.36
     apoder
    -0.35
     gunung
    -0.35
     میان
    -0.35
     integridad
    -0.35
     silvestre
    -0.34
    POSITIVE LOGITS
     orchestra
    0.80
     Orchestra
    0.73
     bands
    0.60
     band
    0.57
    chestra
    0.52
    RunWith
    0.50
    bands
    0.50
     Bands
    0.49
    MLLoader
    0.49
     WebDriverWait
    0.48
    Activations Density 0.046%

    No Known Activations