© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12144
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to crying and heartfelt experiences

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

    sadness (cry, tears, crying)

    np_acts-logits-general · gemini-2.0-flash

    crying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.76
    Tikang
    -0.76
    protoimpl
    -0.64
     estimés
    -0.63
     NUKAT
    -0.63
    AndEndTag
    -0.63
    期刊论文
    -0.60
    tanleria
    -0.59
     "..\..\
    -0.59
     становника
    -0.58
    POSITIVE LOGITS
     tears
    2.36
     crying
    2.20
     Tears
    1.97
    tears
    1.94
     cry
    1.94
     sobbing
    1.94
     cried
    1.91
     wept
    1.90
    Tears
    1.88
     weeping
    1.86
    Activations Density 0.226%

    No Known Activations