© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and personal opinions about various topics, particularly food and entertainment

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

    Positive opinions or sentiments (love, favorite, good)

    np_acts-logits-general · gemini-2.0-flash

    favorite words

    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
     us
    -0.48
    ellyn
    -0.46
     dunque
    -0.46
     diharapkan
    -0.45
     you
    -0.45
     abgerufen
    -0.43
    即可
    -0.42
     nên
    -0.42
    心配
    -0.42
     amaç
    -0.42
    POSITIVE LOGITS
     underrated
    1.00
    Favourite
    0.97
    IntoConstraints
    0.96
    بوابة
    0.96
     adoro
    0.94
    Favorite
    0.93
     favorite
    0.92
     favourite
    0.91
     Favourite
    0.90
     Favorite
    0.89
    Activations Density 0.193%

    No Known Activations