© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3419
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reasons or causes for events

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

    phrases containing the words "due to".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    causal prepositional reason phrases (the “because of” construction), with occasional activation for deadline/obligation uses of “due.”

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the phrase "due to" (specifically the word "due" when followed by "to").

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     commandement
    -0.64
    ſelf
    -0.60
     inoxydable
    -0.57
     perſon
    -0.56
     plastiques
    -0.52
    readString
    -0.51
     financières
    -0.51
     enfans
    -0.49
     ſtill
    -0.49
     Erziehung
    -0.48
    POSITIVE LOGITS
     due
    1.05
     DUE
    1.02
     Due
    0.95
    due
    0.95
    DUE
    0.92
    Due
    0.91
     ब्रेकडाउन
    0.75
     devido
    0.71
    adaptiveStyles
    0.68
     Bue
    0.65
    Activations Density 0.053%

    No Known Activations