© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11541
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to limits and asymptotic behavior

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

    Expressions with "limit" or "tends to"

    np_acts-logits-general · gemini-2.0-flash

    calculating mathematical limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.68
     незавершена
    -0.60
     defaultstate
    -0.54
    $_['
    -0.53
     виправивши
    -0.51
     Aquila
    -0.47
    Tē
    -0.46
     IndexPath
    -0.45
     دوس
    -0.45
    alité
    -0.45
    POSITIVE LOGITS
     limit
    1.55
    lim
    1.32
     lim
    1.30
     Limit
    1.29
    limit
    1.28
    Limit
    1.24
     limits
    1.23
     LIMIT
    1.18
     limite
    1.15
     limiting
    1.14
    Activations Density 1.459%

    No Known Activations