© 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. 10822
    Prev
    Next
    INDEX
    Explanations

    references to poor conditions, whether related to health, economic status, or quality of life

    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
    AddTagHelper
    -0.69
     Савезне
    -0.65
     autorytatywna
    -0.61
    SequentialGroup
    -0.58
     surla
    -0.57
     تعدى
    -0.56
    parsedMessage
    -0.55
     kaarangay
    -0.54
     Infórmanos
    -0.54
     unmute
    -0.54
    POSITIVE LOGITS
     poor
    1.44
    Poor
    1.36
    poor
    1.35
     Poor
    1.32
     POOR
    1.27
     poorly
    1.20
     crappy
    1.10
     substandard
    1.07
     inadequate
    1.04
     dårlig
    1.04
    Activations Density 1.878%

    No Known Activations