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-2-2B
    4. Residual Stream - 65k
    5. 17-GEMMASCOPE-RES-65K
    6. 28490
    Prev
    Next
    INDEX
    Explanations

    terms related to astronomical phenomena and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_65k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eslint
    -0.53
    AsUp
    -0.50
     gericht
    -0.50
    Palmarès
    -0.49
     BoxDecoration
    -0.48
    ografía
    -0.48
     vests
    -0.47
    HINT
    -0.47
    iestety
    -0.47
    ꒳
    -0.47
    POSITIVE LOGITS
     amazement
    1.02
     awe
    0.99
     astonishment
    0.89
     amazed
    0.85
     astonished
    0.84
     exclaim
    0.79
     marvels
    0.77
     amaze
    0.76
     shocked
    0.74
     asomb
    0.73
    Activations Density 0.096%

    No Known Activations