© 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. 8489
    Prev
    Next
    INDEX
    Explanations

    specific numerical data and measurements, particularly related to dimensions and quantities

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

    Dimensions with × or x

    np_acts-logits-general · gemini-2.0-flash

    dimensions and multiplication

    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
     تضيفلها
    -0.96
    AccessorTable
    -0.96
     незавершена
    -0.87
    MessageTagHelper
    -0.83
     initComponents
    -0.80
    BufferException
    -0.79
    tagHelperRunner
    -0.79
    featureID
    -0.78
    UrlResolution
    -0.76
    EndContext
    -0.74
    POSITIVE LOGITS
     x
    2.11
     ×
    2.09
    ×
    1.98
    x
    1.68
     X
    1.42
     × 
    1.39
    times
    1.33
    ×</
    1.23
    ｘ
    1.22
    X
    1.19
    Activations Density 0.608%

    No Known Activations