© 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. 21-GEMMASCOPE-RES-16K
    11. 1310
    Prev
    Next
    INDEX
    Explanations

    terms related to discs and their associated properties

    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
    abestanden
    -0.93
    WebVitals
    -0.80
    PyExc
    -0.79
    httphttps
    -0.78
    interopRequire
    -0.74
    Panamoan
    -0.73
    endphp
    -0.70
    CGContext
    -0.68
    duire
    -0.66
    __*/
    -0.66
    POSITIVE LOGITS
     DIS
    0.59
    DIS
    0.57
     skimage
    0.55
     useDispatch
    0.55
    DSC
    0.54
     Réponses
    0.53
     Brü
    0.49
     Donc
    0.49
    :+:
    0.49
    epam
    0.48
    Activations Density 0.191%

    No Known Activations