© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10586
    Prev
    Next
    INDEX
    Explanations

    references to the concept of holiness or religious authority

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

    "Holy" followed by a place or religious noun

    np_acts-logits-general · gemini-2.0-flash

    holy roman

    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
    AccessorTable
    -1.01
     EconPapers
    -0.97
    RectangleBorder
    -0.93
     الحره
    -0.92
     незавершена
    -0.90
    httphttps
    -0.90
    InSection
    -0.88
    AndEndTag
    -0.85
     صوتيه
    -0.85
    ViewFeatures
    -0.82
    POSITIVE LOGITS
    oke
    0.72
     grail
    0.66
     Spirit
    0.60
    Spirit
    0.54
    scriptcase
    0.53
     Cross
    0.52
     Ghost
    0.52
     Land
    0.52
     cow
    0.50
    trinity
    0.49
    Activations Density 0.064%

    No Known Activations