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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15598
    Prev
    Next
    INDEX
    Explanations

    mentions of company founding and business operations

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

    Past tense verbs/auxiliaries

    np_acts-logits-general · gemini-2.0-flash

    at that time

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     today
    -1.50
     tonight
    -1.45
     σήμερα
    -1.31
    today
    -1.31
     tomorrow
    -1.30
     todays
    -1.28
     сегодня
    -1.25
     сьогодні
    -1.24
     امروز
    -1.16
     vandaag
    -1.15
    POSITIVE LOGITS
     damals
    1.22
     then
    1.20
     тогда
    1.17
     alors
    1.15
    當時
    1.15
     damal
    1.14
    当时
    1.13
    当时的
    1.09
    当時
    1.09
     então
    1.08
    Activations Density 0.621%

    No Known Activations