© 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. 4-GEMMASCOPE-RES-16K
    11. 11538
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming syntax related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Identyfik
    -0.66
    OrNil
    -0.64
    MemoryWarning
    -0.62
     muualla
    -0.61
    VIAF
    -0.59
    Notae
    -0.58
     externi
    -0.58
    envolvimento
    -0.58
    ://$
    -0.57
    amental
    -0.57
    POSITIVE LOGITS
    sizeCache
    0.56
    awaiter
    0.56
    BoxShadow
    0.54
     onOptions
    0.52
    +#+#
    0.49
    PositiveButton
    0.49
     विश्वसनीयता
    0.48
    levé
    0.47
     DialogInterface
    0.47
    RefreshLayout
    0.46
    Activations Density 4.056%

    No Known Activations