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. 4-GEMMASCOPE-RES-16K
    6. 11104
    Prev
    Next
    INDEX
    Explanations

    concepts related to spiritual and mental control practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gráfica
    -0.59
     unwritten
    -0.51
    )<<
    -0.51
    uscular
    -0.51
     Eton
    -0.51
    tvguidetime
    -0.50
    htë
    -0.50
    chtenstein
    -0.50
    −/−
    -0.48
     PublicKey
    -0.48
    POSITIVE LOGITS
     meditation
    0.99
    Meditation
    0.96
     yoga
    0.94
     Yoga
    0.92
     Meditation
    0.92
    Yoga
    0.91
    meditation
    0.85
     meditations
    0.81
     YOGA
    0.79
     meditate
    0.78
    Activations Density 1.136%

    No Known Activations