Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 24544
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and key attributes related to processes and systems

    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
     EconPapers
    -0.80
    AccessorTable
    -0.79
     Biôgrafia
    -0.77
    Życiorys
    -0.75
    AddTagHelper
    -0.75
     laſſen
    -0.74
    Tikang
    -0.74
    niſſe
    -0.73
     Geſch
    -0.72
     increí
    -0.72
    POSITIVE LOGITS
     mes
    0.39
    is
    0.39
     
    0.38
     ob
    0.38
    mes
    0.38
    ,
    0.36
    ab
    0.36
    bil
    0.35
     w
    0.35
    cal
    0.35
    Activations Density 0.066%

    No Known Activations