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. 2630
    Prev
    Next
    INDEX
    Explanations

    references to astronomical phenomena and their effects

    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
     performance
    -0.50
    ComponentModel
    -0.48
    花板
    -0.46
    /
    -0.46
     Riverdale
    -0.45
     requestId
    -0.45
     Performance
    -0.45
    зирован
    -0.44
     Lipschitz
    -0.43
     I
    -0.43
    POSITIVE LOGITS
    Portale
    0.82
     découver
    0.79
    awtextra
    0.73
     scolaires
    0.73
     UnityEditor
    0.71
    PreferredItem
    0.71
     astronomers
    0.70
     énergé
    0.70
     médicaux
    0.69
     géant
    0.68
    Activations Density 0.270%

    No Known Activations