© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    elements related to mythology and magical realism

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

    Abstract concepts (e.g., life, death, humanity)

    np_acts-logits-general · gemini-2.0-flash

    God, evil, he

    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
    ConfigureAwait
    -0.54
     affichés
    -0.53
     morado
    -0.51
     surpren
    -0.50
    namese
    -0.49
     dovuto
    -0.49
     ferons
    -0.48
    SqlSession
    -0.46
     <>",
    -0.46
     rédaction
    -0.45
    POSITIVE LOGITS
     life
    1.13
     death
    1.00
     humanity
    0.99
     freedom
    0.90
     reality
    0.89
     mankind
    0.89
     darkness
    0.87
     happiness
    0.86
     civilization
    0.84
     justice
    0.81
    Activations Density 0.839%

    No Known Activations