© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    conversational language and questions regarding actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RegressionTest
    -0.96
    PMailer
    -0.88
     autorytatywna
    -0.71
     firent
    -0.71
    PerformLayout
    -0.69
     חיצוניים
    -0.68
    windowFixed
    -0.68
    tront
    -0.65
    DoubleQuotes
    -0.65
    Xna
    -0.65
    POSITIVE LOGITS
    atzen
    0.54
     sometimes
    0.46
     occasionally
    0.44
     frequently
    0.44
     occasions
    0.43
     Sometimes
    0.43
    дря
    0.41
     geli
    0.41
    Sometimes
    0.41
     Occasionally
    0.40
    Activations Density 0.011%

    No Known Activations