© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 13836
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rätt
    -0.43
     africains
    -0.40
     textes
    -0.38
     kjem
    -0.37
     débats
    -0.37
     noires
    -0.37
     locaux
    -0.37
    gående
    -0.36
     ansatte
    -0.36
     gestes
    -0.35
    POSITIVE LOGITS
     until
    1.55
     Until
    1.49
    until
    1.48
    Until
    1.45
     untill
    1.29
     UNTIL
    1.26
     till
    1.12
     Till
    1.11
    直到
    1.07
    Till
    1.01
    Activations Density 0.073%

    No Known Activations