© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 106119
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to art, creativity, and personal expression

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

    Catchy phrases, idioms, or wordplay that grab attention, particularly in titles, promotional content, or creative writing.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     fevere
    -0.62
     StatefulWidget
    -0.61
     ſever
    -0.54
     StatelessWidget
    -0.54
    PathVariable
    -0.53
     ddelweddau
    -0.50
    mariage
    -0.47
    Fatalf
    -0.47
     zoude
    -0.46
     diſt
    -0.46
    POSITIVE LOGITS
    AnimationsModule
    0.51
     nonUne
    0.47
    expandindo
    0.41
     تانيه
    0.40
    RunWith
    0.40
     '\\;'
    0.39
     lenker
    0.39
    ⤹
    0.38
    🎳
    0.38
    ∎
    0.37
    Activations Density 0.039%

    No Known Activations