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. 114897
    Prev
    Next
    INDEX
    Explanations

    phrases related to priorities and considerations

    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
     notables
    -0.40
    MessageTagHelper
    -0.39
     Lern
    -0.39
     fanciful
    -0.38
     Kräuter
    -0.38
     Erben
    -0.38
     Marín
    -0.38
     notable
    -0.37
    UNICODE
    -0.37
     vinto
    -0.37
    POSITIVE LOGITS
     priority
    0.73
     priorities
    0.66
     prioriti
    0.64
     priorité
    0.62
     tartalomajánló
    0.61
    priority
    0.61
     prioritize
    0.60
     Priority
    0.58
    優先
    0.57
     prioridad
    0.57
    Activations Density 0.023%

    No Known Activations