© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3387
    Prev
    Next
    INDEX
    Explanations

    references to the genre of rock music and related terminology

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

    "Rock" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    rock followed by another word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     оригіналу
    -0.64
     disambiguazione
    -0.64
    mability
    -0.61
    xase
    -0.60
     Helios
    -0.58
     Smithfield
    -0.57
     Janus
    -0.56
    WireFormatLite
    -0.55
     kysy
    -0.54
     Checkpoint
    -0.53
    POSITIVE LOGITS
     Rock
    0.75
     ROCK
    0.71
    Rock
    0.71
     rock
    0.70
    rock
    0.70
    ROCK
    0.66
    efeller
    0.62
    toHaveBeenCalled
    0.61
    stars
    0.59
    eting
    0.58
    Activations Density 0.054%

    No Known Activations