© 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. 14-GEMMASCOPE-RES-16K
    11. 8531
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate roles, classifications, and influences related to authority and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tilities
    -0.50
     linkovi
    -0.48
    sipasi
    -0.46
    󠁣
    -0.45
    ymal
    -0.44
    oforms
    -0.42
     wikipagina
    -0.42
     εί
    -0.40
    isasi
    -0.40
    arrange
    -0.40
    POSITIVE LOGITS
    withOpacity
    0.57
     TextAppearance
    0.46
     committed
    0.45
    WithMany
    0.45
    RRect
    0.40
    Formik
    0.40
    PyExc
    0.39
     caring
    0.39
    aurait
    0.38
    Trichloroethane
    0.38
    Activations Density 0.419%

    No Known Activations