© 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. 25-GEMMASCOPE-RES-16K
    6. 9057
    Prev
    Next
    INDEX
    Explanations

    references to themes of divinity and spirituality

    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
     <=",
    -0.81
    IUrlHelper
    -0.76
    期刊论文
    -0.63
    NameInMap
    -0.61
     resourceCulture
    -0.59
     дописавши
    -0.54
     informée
    -0.53
    RUnlock
    -0.53
    inerja
    -0.53
    новниш
    -0.51
    POSITIVE LOGITS
     heaven
    0.64
     laws
    0.64
     avenue
    0.61
     Avenue
    0.59
     Laws
    0.58
    Laws
    0.57
     supreme
    0.56
     heavenly
    0.55
     Dao
    0.55
     law
    0.53
    Activations Density 0.071%

    No Known Activations