© 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. 18-GEMMASCOPE-RES-16K
    6. 11688
    Prev
    Next
    INDEX
    Explanations

    references to religious themes or concepts

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

    Following numbers or numerical ranges

    np_acts-logits-general · gemini-2.0-flash

    Apocalypse and Revelation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.66
    帖最后由
    -0.58
     *)__
    -0.55
    曖昧さ回避
    -0.55
    )_/¯
    -0.52
     توج
    -0.52
    xically
    -0.51
     يتيمه
    -0.50
     HOM
    -0.50
     متعلقه
    -0.50
    POSITIVE LOGITS
     Revelation
    0.71
    Revelation
    0.65
    Revel
    0.56
    amazonaws
    0.56
     Rev
    0.56
    Rev
    0.56
     Revel
    0.55
     Seals
    0.54
     Apocalypse
    0.54
    Sealed
    0.52
    Activations Density 0.200%

    No Known Activations