© 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. 25-GEMMASCOPE-RES-16K
    11. 2989
    Prev
    Next
    INDEX
    Explanations

    terms related to authority within religious contexts, particularly in relation to church governance and doctrine

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

    references to religious authority and doctrines within denominations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.69
    TypedDataSet
    -0.65
    nocache
    -0.59
    enteuer
    -0.55
     виправивши
    -0.54
    geord
    -0.53
     Timor
    -0.52
    JAXB
    -0.52
     везе
    -0.50
    pyx
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.61
     Sola
    0.61
     magister
    0.60
     sola
    0.60
    Sola
    0.58
    sola
    0.58
     Magister
    0.57
    ⓘ
    0.53
     councils
    0.53
     dog
    0.52
    Activations Density 0.374%

    No Known Activations