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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8198
    Prev
    Next
    INDEX
    Explanations

    concepts and phrases related to healing and its benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gher
    -0.45
    getElements
    -0.40
     béo
    -0.38
     Fermi
    -0.38
     mèo
    -0.38
     stupidly
    -0.37
     Biele
    -0.37
     knuckle
    -0.37
     headless
    -0.36
     smuggling
    -0.36
    POSITIVE LOGITS
     healing
    1.05
     Healing
    0.93
    healing
    0.92
    Healing
    0.89
     therapeutic
    0.82
     heals
    0.79
     curative
    0.78
     restorative
    0.77
     heal
    0.77
    therapeutic
    0.77
    Activations Density 0.018%

    No Known Activations