© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues and symptoms

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

    children's activities or play

    np_acts-logits-general · gemini-2.0-flash

    childhood play and activities

    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
     ब्रेकडाउन
    -0.66
     étudiants
    -0.60
    abol
    -0.59
     mahasiswa
    -0.58
     студентов
    -0.58
    NewUrlParser
    -0.55
     collè
    -0.55
    若い
    -0.54
     vrouwen
    -0.54
     žen
    -0.53
    POSITIVE LOGITS
     toys
    1.13
     toy
    1.03
     playground
    0.98
     Toys
    0.93
     playtime
    0.93
     play
    0.90
    Toys
    0.86
    toys
    0.85
    toy
    0.82
     Play
    0.82
    Activations Density 0.311%

    No Known Activations