© 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. 20-GEMMASCOPE-RES-16K
    6. 15903
    Prev
    Next
    INDEX
    Explanations

    words expressing strong emotions or states of feeling

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

    Informal communicative text (internet slang)

    np_acts-logits-general · gemini-2.0-flash

    Filipino words and phrases

    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
    AndEndTag
    -0.96
     purpoſe
    -0.89
     itſelf
    -0.87
    RenderAtEndOf
    -0.86
     houſe
    -0.83
     تضيفلها
    -0.82
    存于互联网档案馆
    -0.82
     faſt
    -0.82
     raiſ
    -0.82
    Datuak
    -0.81
    POSITIVE LOGITS
     pag
    0.60
     sa
    0.59
     mag
    0.57
     na
    0.57
     ka
    0.50
     ang
    0.50
     tal
    0.50
     nag
    0.50
     Sa
    0.48
     may
    0.48
    Activations Density 0.010%

    No Known Activations