Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8774
    Prev
    Next
    INDEX
    Explanations

    references to the concept of spirit or spirituality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.87
     <>",
    -0.84
     utafitiHapana
    -0.83
     ◄
    -0.82
     Faire
    -0.81
     Maximus
    -0.81
    verwijspagina
    -0.80
    ///</
    -0.80
    Рабо
    -0.79
     Ptole
    -0.78
    POSITIVE LOGITS
     Spirit
    1.65
     spirit
    1.47
     Spirits
    1.46
    Spirit
    1.45
     SPIRIT
    1.41
     spirits
    1.38
    spirit
    1.35
    Spir
    1.07
    geist
    1.04
    Esprit
    1.04
    Activations Density 0.127%

    No Known Activations