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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9070
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in various contexts

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

    Punctuation after sentences

    np_acts-logits-general · gemini-2.0-flash

    firstly, namely, because

    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
     entanto
    -0.85
    complexContent
    -0.80
     then
    -0.80
     entonces
    -0.71
     also
    -0.69
    
    -0.69
    Then
    -0.69
     asimismo
    -0.68
     также
    -0.68
     همچنین
    -0.68
    POSITIVE LOGITS
     nämlich
    1.28
     nemlig
    1.25
     Namely
    1.18
     Firstly
    1.17
     totiž
    1.15
    Firstly
    1.14
     namelijk
    1.11
     bowiem
    1.05
     Ведь
    1.03
    というのも
    0.98
    Activations Density 0.383%

    No Known Activations