© 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. 27-GEMMASCOPE-RES-16K
    11. 9650
    Prev
    Next
    INDEX
    Explanations

    phrases related to appointments and financial aid processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Entstehung
    -0.55
     Entste
    -0.50
     Verhält
    -0.46
     Nutzen
    -0.45
     Begriffe
    -0.43
     Strukturen
    -0.43
     Begriff
    -0.41
     Ursache
    -0.41
     Erhöhung
    -0.41
     Feinde
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.89
    AndEndTag
    0.84
    niſſe
    0.77
     pleaſure
    0.71
     nakalista
    0.71
     houſe
    0.71
     episcopal
    0.69
    ſammen
    0.69
     pedic
    0.68
    uxxxx
    0.67
    Activations Density 1.856%

    No Known Activations