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-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 777
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to legal proceedings and testimonies

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

    references to historical or narrative elements involving characters and their actions

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

    past perfect tense with "had"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    PONENT
    -0.55
     Went
    -0.54
    orianCalendar
    -0.54
    contentLoaded
    -0.54
     Became
    -0.52
     Wrote
    -0.52
     Began
    -0.51
    ίκη
    -0.50
    dolu
    -0.49
    went
    -0.49
    POSITIVE LOGITS
     hadn
    1.43
     habían
    1.28
     had
    1.26
     había
    1.07
     havia
    0.93
     hadden
    0.89
    had
    0.87
     aveva
    0.87
     avaient
    0.86
     havi
    0.85
    Activations Density 0.477%

    No Known Activations