© 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. 11-GEMMASCOPE-RES-16K
    11. 10000
    Prev
    Next
    INDEX
    Explanations

    terms related to adversarial entities or threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erſt
    -0.73
     dieſer
    -0.72
     verſch
    -0.72
     müſſen
    -0.71
     wiſſen
    -0.70
     unſer
    -0.70
     ſeinem
    -0.69
     ſelbſt
    -0.69
     ſans
    -0.69
     ſeinen
    -0.69
    POSITIVE LOGITS
     enemy
    1.33
     opponent
    1.21
     opponents
    1.20
    enemy
    1.08
     enemies
    1.07
     Enemy
    1.07
     musuh
    1.05
     adversaries
    1.02
    Enemy
    1.00
     enemigo
    0.98
    Activations Density 0.277%

    No Known Activations