© 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. 0-GEMMASCOPE-RES-16K
    11. 15013
    Prev
    Next
    INDEX
    Explanations

    references to debates and discussions on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jar
    -0.54
    pit
    -0.51
    rob
    -0.51
    NIL
    -0.50
    circ
    -0.50
    deg
    -0.50
    dart
    -0.50
    tid
    -0.50
     NIL
    -0.49
    ars
    -0.49
    POSITIVE LOGITS
     enfans
    0.87
     Monfieur
    0.84
     desmotivaciones
    0.81
     Houſe
    0.81
     navideño
    0.79
     navideños
    0.77
     myſelf
    0.75
     houſe
    0.75
     näytte
    0.73
     Anſ
    0.73
    Activations Density 0.248%

    No Known Activations