© 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. 19-GEMMASCOPE-RES-16K
    6. 10908
    Prev
    Next
    INDEX
    Explanations

    discussions related to sympathy and support in times of loss or hardship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Abitanti
    -0.45
    :]:
    -0.45
     فريبيس
    -0.43
     plaisir
    -0.42
    parsedMessage
    -0.41
    изнь
    -0.41
     inden
    -0.41
    こちら
    -0.40
     xong
    -0.40
    UserScript
    -0.40
    POSITIVE LOGITS
     amid
    1.09
     times
    1.07
     amidst
    1.05
     during
    1.05
    during
    0.98
     current
    0.97
     tijden
    0.96
     DURING
    0.95
     Amid
    0.95
     CURRENT
    0.94
    Activations Density 0.166%

    No Known Activations