© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14927
    Prev
    Next
    INDEX
    Explanations

    elements related to religious themes and apocalyptic events

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

    end times or prophecy

    np_acts-logits-general · gemini-2.0-flash

    apocalyptic prophecies and end times

    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
    #+#
    -0.67
    DrawerToggle
    -0.51
     تعدى
    -0.51
     Steck
    -0.49
    nesc
    -0.47
     donor
    -0.47
     delic
    -0.47
     useAuth
    -0.46
    ⁡
    -0.46
    Mixin
    -0.46
    POSITIVE LOGITS
     apocalyptic
    0.76
     prophe
    0.72
    HtmlAttribute
    0.70
     foretold
    0.68
     prediction
    0.68
     prophecy
    0.66
     Armageddon
    0.64
     prophecies
    0.63
     prophetic
    0.63
     apocalypse
    0.63
    Activations Density 0.136%

    No Known Activations