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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5528
    Prev
    Next
    INDEX
    Explanations

    emojis and other symbols representing emotions or food

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

    Emojis followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    emojis and gender symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ã
    -0.55
     \"
    -0.48
     "
    -0.45
     '
    -0.43
    |/
    -0.43
    áu
    -0.43
    Biographie
    -0.42
     \{
    -0.42
     mati
    -0.41
     Architekten
    -0.41
    POSITIVE LOGITS
    󠁢
    0.76
     bivolt
    0.73
    elemField
    0.71
     Cæsar
    0.70
     Савезне
    0.69
     Jefus
    0.69
     itſelf
    0.66
    🏻
    0.66
    ️
    0.64
     Efq
    0.64
    Activations Density 0.071%

    No Known Activations