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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 3577
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to lamp design and efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CARTOON
    -0.48
     disambiguazione
    -0.46
    ocardio
    -0.46
     Mure
    -0.43
     Срби
    -0.43
    omt
    -0.43
    antine
    -0.42
     Letting
    -0.42
     Hear
    -0.42
    kloped
    -0.42
    POSITIVE LOGITS
     fixture
    0.87
     CRI
    0.82
     Fixture
    0.75
     fixtures
    0.74
    Fixture
    0.70
    CRI
    0.69
    \{\\
    0.67
    COB
    0.67
     COB
    0.67
     diffuser
    0.67
    Activations Density 0.124%

    No Known Activations