© 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. 11120
    Prev
    Next
    INDEX
    Explanations

    expressions that relate to perception and understanding of emotions or qualities

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

    "Sense" followed by a quality or emotion

    np_acts-logits-general · gemini-2.0-flash

    sense of

    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
    ništvo
    -0.50
    aska
    -0.50
     Bancroft
    -0.49
    getInfo
    -0.49
    İstinadlar
    -0.47
    ífica
    -0.47
    )$/,
    -0.47
    ه‌ای
    -0.46
    apin
    -0.46
     صلى
    -0.45
    POSITIVE LOGITS
     humor
    0.75
     urgency
    0.75
     smell
    0.74
     Smell
    0.74
     SENSE
    0.74
    Tikang
    0.73
     humour
    0.73
     Humor
    0.71
    ChildScrollView
    0.71
    smell
    0.69
    Activations Density 0.047%

    No Known Activations