© 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. 2-GEMMASCOPE-RES-16K
    11. 13050
    Prev
    Next
    INDEX
    Explanations

    instances of the word "appointed" and related terms that suggest official appointments or assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/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.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     createState
    -0.42
     hroz
    -0.40
     lançado
    -0.37
    NamedQueries
    -0.35
    roen
    -0.34
     lanzado
    -0.33
     wier
    -0.33
    Descubre
    -0.33
     purely
    -0.33
    FlatStyle
    -0.33
    POSITIVE LOGITS
     attempted
    0.94
    Seeking
    0.80
     Seeking
    0.79
     attempting
    0.75
     seeking
    0.73
     sought
    0.73
    seeking
    0.68
     appointment
    0.65
     Appointment
    0.62
    Appointment
    0.61
    Activations Density 0.147%

    No Known Activations