© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 9711
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or expressions indicating inclusivity and commonality among individuals or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TDs
    -0.81
     substrates
    -0.80
     sureties
    -0.80
     fellowships
    -0.79
     manifolds
    -0.77
     actuators
    -0.77
     VMs
    -0.77
     avatars
    -0.77
     subclasses
    -0.76
     subdivisions
    -0.76
    POSITIVE LOGITS
     piece
    0.98
     item
    0.93
     member
    0.89
     element
    0.78
     statistic
    0.73
     ingredient
    0.72
     thing
    0.67
     épaules
    0.65
     molecule
    0.65
     parameter
    0.65
    Activations Density 4.854%

    No Known Activations