© 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. 31-GEMMASCOPE-RES-16K
    11. 5503
    Prev
    Next
    INDEX
    Explanations

    references to powerful groups or figures and their potential influence or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conspiracy theories and inflammatory political rhetoric involving accusations against named individuals and organizations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dry
    -0.27
    harapkan
    -0.27
     seca
    -0.26
     koş
    -0.25
     cool
    -0.25
    のよ
    -0.24
    ว
    -0.24
    竞技
    -0.24
     esqu
    -0.23
     complicated
    -0.23
    POSITIVE LOGITS
    conspiracy
    0.88
     conspiracy
    0.84
     conspira
    0.81
    thschild
    0.80
     UFO
    0.75
     Conspiracy
    0.74
     patriots
    0.73
     conspir
    0.73
    rense
    0.73
    vereignty
    0.71
    Activations Density 0.859%

    No Known Activations