© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104627
    Prev
    Next
    INDEX
    Explanations

    concepts related to data analysis and statistics

    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
     réservés
    -0.27
     kiện
    -0.26
     jambe
    -0.26
    isfile
    -0.26
     unters
    -0.26
    AspNetCore
    -0.25
    Carriera
    -0.25
     bas
    -0.25
    Na
    -0.24
     pelo
    -0.24
    POSITIVE LOGITS
     relational
    0.69
     المعيارى
    0.68
    OGND
    0.64
     Informatics
    0.63
     ſche
    0.63
     privacy
    0.62
    privacy
    0.62
     data
    0.62
     otomatig
    0.62
     processing
    0.61
    Activations Density 0.049%

    No Known Activations