© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1957
    Prev
    Next
    INDEX
    Explanations

    themes related to interfaith relationships and the complexities of parenting within differing faith traditions

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

    religion or religious belief

    np_acts-logits-general · gemini-2.0-flash

    religion and faith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     normal
    -0.52
    toFloat
    -0.46
     NORMAL
    -0.44
     nostal
    -0.43
     rotation
    -0.43
    Normal
    -0.43
     rotations
    -0.43
     Normal
    -0.42
     IMPER
    -0.41
     infra
    -0.40
    POSITIVE LOGITS
     religious
    1.10
     religion
    1.03
     Religious
    0.99
     religión
    0.97
     religions
    0.97
    religious
    0.97
     religione
    0.95
     Religion
    0.94
    Religious
    0.92
     Religions
    0.90
    Activations Density 0.530%

    No Known Activations