© 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. 14000
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of intention or future actions

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

    "Going to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    to verb infinitive

    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
     ympä
    -0.52
     esimer
    -0.48
     spiaggia
    -0.48
     mostrarse
    -0.48
     húmedo
    -0.47
     päiv
    -0.47
     decorazione
    -0.46
     orígenes
    -0.45
    hæng
    -0.45
     enää
    -0.45
    POSITIVE LOGITS
     gonna
    0.88
    gonna
    0.84
     GONNA
    0.80
     Gonna
    0.78
    Gonna
    0.76
     be
    0.71
     will
    0.66
     gotta
    0.62
    fortawesome
    0.61
     gon
    0.56
    Activations Density 0.065%

    No Known Activations