© 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. 1-GEMMASCOPE-RES-16K
    6. 3376
    Prev
    Next
    INDEX
    Explanations

    references to music bands and musical group entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    savevideobot
    -0.48
    urbation
    -0.47
     demografica
    -0.47
    veratrol
    -0.45
    aronder
    -0.43
    osexuality
    -0.42
     Administrativna
    -0.42
    lanation
    -0.42
    prefixer
    -0.41
    ographique
    -0.39
    POSITIVE LOGITS
     band
    0.78
     bands
    0.63
     Bands
    0.52
     Stop
    0.49
    Stop
    0.49
    JspWriter
    0.47
     banda
    0.47
     Across
    0.47
    Spo
    0.46
     Starting
    0.46
    Activations Density 0.124%

    No Known Activations