© 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. 1-GEMMASCOPE-RES-16K
    6. 2225
    Prev
    Next
    INDEX
    Explanations

    terms related to telephone communication and reservations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AppCompatTheme
    -0.53
    Ligações
    -0.51
     старости
    -0.50
    setViewportView
    -0.50
    
    -0.49
     مرئيه
    -0.49
     Italijani
    -0.49
    Datuak
    -0.47
    Попис
    -0.47
    Autoritní
    -0.47
    POSITIVE LOGITS
     telephone
    0.91
    telephone
    0.75
     mistaken
    0.71
     reservation
    0.70
     misunderstand
    0.68
     Reservation
    0.67
     reservations
    0.66
     Reservations
    0.66
     confusión
    0.65
     mistake
    0.63
    Activations Density 0.194%

    No Known Activations