© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11001
    Prev
    Next
    INDEX
    Explanations

    references to religious doctrines and authority structures

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

    Religious creeds, teachings, and denominations

    np_acts-logits-general · gemini-2.0-flash

    religious doctrines and denominations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dedicated
    -0.35
     gre
    -0.35
     dedica
    -0.33
     VIP
    -0.31
     auction
    -0.31
    Proc
    -0.30
     receivers
    -0.30
     auctions
    -0.30
    proc
    -0.29
    licet
    -0.29
    POSITIVE LOGITS
    enderror
    0.79
     للاسماء
    0.63
     kasarigan
    0.60
    fjspx
    0.59
     CURIAM
    0.56
    endpush
    0.56
    httphttps
    0.55
    IUrlHelper
    0.55
    存于互联网档案馆
    0.54
     autorytatywna
    0.54
    Activations Density 0.350%

    No Known Activations