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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113831
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    0 followed by x or user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     незавершена
    -0.67
    TestingModule
    -0.65
    TemporalType
    -0.59
     StatefulWidget
    -0.58
    saraba
    -0.55
     مشين
    -0.54
    PickerController
    -0.53
     EconPapers
    -0.53
     contextLoads
    -0.52
     дописавши
    -0.52
    POSITIVE LOGITS
     little
    0.38
    aClass
    0.38
     bitterness
    0.36
     caneta
    0.36
     chronological
    0.36
     propOrder
    0.35
     surpresa
    0.35
     vergüenza
    0.35
     discreet
    0.35
     obserw
    0.35
    Activations Density 0.000%

    No Known Activations