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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3577
    Prev
    Next
    INDEX
    Explanations

    descriptions of musical performance dynamics and collaboration among artists

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

    music and musicians

    np_acts-logits-general · gemini-2.0-flash

    music and songs by different artists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kezés
    -0.49
     polaire
    -0.49
    readObject
    -0.47
     kyl
    -0.47
    ulents
    -0.47
     sī
    -0.46
    ıntı
    -0.46
    sightly
    -0.46
    RenderAtEndOf
    -0.45
    ReadInt
    -0.45
    POSITIVE LOGITS
     music
    2.35
     musical
    2.14
     musically
    2.04
    music
    1.99
     musicians
    1.97
     songs
    1.96
     Music
    1.93
     song
    1.86
    Music
    1.85
    musical
    1.78
    Activations Density 0.954%

    No Known Activations