© 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. 24-GEMMASCOPE-RES-16K
    6. 3963
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional relief and personal reflection related to activities like sewing and tea drinking

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

    "to" followed by an action/infinitive

    np_acts-logits-general · gemini-2.0-flash

    unwind and relax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Baillargeon
    -0.59
    eraard
    -0.53
    тябрь
    -0.51
    boda
    -0.51
    PAIGN
    -0.51
    cader
    -0.50
    onViewCreated
    -0.47
     prová
    -0.47
     опа
    -0.46
    criminate
    -0.46
    POSITIVE LOGITS
     recharge
    1.08
     relaxation
    1.03
     unwind
    0.99
     calm
    0.99
     tranquility
    0.98
     calming
    0.96
     peace
    0.96
     Recharge
    0.95
     respite
    0.94
     serenity
    0.92
    Activations Density 0.157%

    No Known Activations