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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4645
    Prev
    Next
    INDEX
    Explanations

    elements related to string manipulation and file handling in programming

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

    immediately followed by punctuation

    np_acts-logits-general · gemini-2.0-flash

    Day parts

    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
     whereof
    -0.72
    mybatisplus
    -0.66
     viewDidLoad
    -0.64
     kasarigan
    -0.62
     DHT
    -0.62
     المعيارى
    -0.60
     lemmas
    -0.59
    AFX
    -0.58
     anvil
    -0.58
    WebServlet
    -0.58
    POSITIVE LOGITS
     Day
    0.65
    Day
    0.61
    day
    0.55
     Advent
    0.55
     day
    0.54
     Part
    0.51
    DAY
    0.50
     fuel
    0.49
     DAY
    0.49
    Part
    0.49
    Activations Density 0.075%

    No Known Activations