© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6994
    Prev
    Next
    INDEX
    Explanations

    discussions about delaying or postponing significant life events, particularly parenthood

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

    delaying or waiting

    np_acts-logits-general · gemini-2.0-flash

    delay or postponement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    unmodifiable
    -0.38
     schnell
    -0.35
     rapidamente
    -0.32
     quick
    -0.32
     quickly
    -0.32
    你了
    -0.30
    responseCode
    -0.30
     rychle
    -0.30
     rápida
    -0.30
     rapid
    -0.30
    POSITIVE LOGITS
     delaying
    0.79
     delay
    0.79
     delayed
    0.78
     Delayed
    0.78
     postpone
    0.78
     Delay
    0.76
     DELAY
    0.74
    Delay
    0.73
     postponement
    0.70
    delay
    0.68
    Activations Density 0.300%

    No Known Activations