© 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. 31-GEMMASCOPE-RES-16K
    11. 1515
    Prev
    Next
    INDEX
    Explanations

    references to legislation concerning national security and terrorism

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

    references to terrorism, terrorist attacks, and related security concerns.

    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
    ClInclude
    -0.33
    dasarkan
    -0.31
     bra
    -0.30
     dziel
    -0.30
     createSprite
    -0.29
     folha
    -0.29
     rozwią
    -0.29
     drodze
    -0.29
     eléctricos
    -0.28
     Expédié
    -0.28
    POSITIVE LOGITS
     terrorist
    1.20
     terrorists
    1.13
    terror
    1.09
     terrorism
    1.09
     Terror
    1.02
    Terror
    1.02
     Terrorism
    0.98
    terrorism
    0.97
     Osama
    0.96
     terror
    0.93
    Activations Density 0.262%

    No Known Activations