© 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. 15-GEMMASCOPE-RES-16K
    6. 866
    Prev
    Next
    INDEX
    Explanations

    references to music-related content and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    égio
    -0.44
     civil
    -0.42
    prnewswire
    -0.36
    ベーター
    -0.36
     INTERESAR
    -0.36
     Civil
    -0.35
     kald
    -0.35
     Noon
    -0.35
     complements
    -0.35
     tegas
    -0.35
    POSITIVE LOGITS
     music
    1.26
    music
    1.09
     musical
    1.06
     musicians
    1.06
     Music
    1.05
     musicale
    1.04
     MUSIC
    1.03
    Music
    1.01
     musik
    1.01
     muziek
    0.99
    Activations Density 0.780%

    No Known Activations