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. 102974
    Prev
    Next
    INDEX
    Explanations

    references to energy manipulation and transformation

    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
    rungsseite
    -0.75
    __(/*!
    -0.67
    ########.
    -0.67
     EconPapers
    -0.67
    ("")]
    
    -0.63
    ReusableCell
    -0.62
    richTextPanel
    -0.61
    ModelAdmin
    -0.61
     Wikiseite
    -0.59
    expandindo
    -0.58
    POSITIVE LOGITS
     energy
    0.45
     energies
    0.43
     flows
    0.39
     deposits
    0.37
     particles
    0.37
     flow
    0.36
     energie
    0.34
     Mist
    0.33
     reserves
    0.32
    energies
    0.32
    Activations Density 0.025%

    No Known Activations