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. 22386
    Prev
    Next
    INDEX
    Explanations

    concerns related to economic indicators and funding in various contexts

    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
     ujednoznacz
    -0.56
     another
    -0.46
    fromnode
    -0.45
     nader
    -0.43
    another
    -0.42
    ьаж
    -0.42
     brief
    -0.42
     seldom
    -0.41
    Примечания
    -0.41
     SIO
    -0.40
    POSITIVE LOGITS
     Semua
    0.65
     everything
    0.65
    Everything
    0.61
    Semua
    0.60
     Everything
    0.58
     všetky
    0.58
    everything
    0.57
     wszystkie
    0.57
     всички
    0.57
     Todas
    0.56
    Activations Density 0.063%

    No Known Activations