© 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. 8182
    Prev
    Next
    INDEX
    Explanations

    positive descriptors and terms related to challenges or difficulties in personal finance and health contexts

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

    Adjective before a noun

    np_acts-logits-general · gemini-2.0-flash

    adjectives followed by nouns

    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
    roughly
    -0.70
     decidedly
    -0.66
     nécessairement
    -0.60
     admittedly
    -0.58
     preen
    -0.57
     lentement
    -0.57
     particularmente
    -0.57
     ligeramente
    -0.56
     roughly
    -0.54
     Roughly
    -0.54
    POSITIVE LOGITS
     stuffs
    0.88
     evidences
    0.84
     advices
    0.81
     ones
    0.80
     equipments
    0.78
     researches
    0.77
     ترین
    0.71
     matured
    0.70
    ness
    0.69
    NumOf
    0.69
    Activations Density 0.642%

    No Known Activations