© 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. 22-GEMMASCOPE-RES-16K
    11. 12484
    Prev
    Next
    INDEX
    Explanations

    details about artificial neural network architectures and their configurations

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

    Tokens related to neural networks or hidden layers

    np_acts-logits-general · gemini-2.0-flash

    hidden neural network layers

    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
    +#+#
    -0.78
    IntoConstraints
    -0.74
     дописавши
    -0.63
    
    -0.62
    :✨
    -0.61
     JpaRepository
    -0.59
    iecie
    -0.58
    CloseOperation
    -0.55
    ----</
    -0.53
    dataclass
    -0.52
    POSITIVE LOGITS
     hidden
    0.86
     neural
    0.86
    Hidden
    0.83
     Neural
    0.82
     activation
    0.82
     neurons
    0.81
     Hidden
    0.80
     neur
    0.78
     neuron
    0.76
     concealed
    0.74
    Activations Density 0.340%

    No Known Activations