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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5403
    Prev
    Next
    INDEX
    Explanations

    references to surveillance and recording devices

    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
    Халык
    -0.43
     Réponses
    -0.40
    peza
    -0.40
    Solución
    -0.40
    ksesta
    -0.38
     رم
    -0.36
    banco
    -0.36
    Reparto
    -0.35
    cemment
    -0.35
     Boucher
    -0.35
    POSITIVE LOGITS
     video
    0.65
    video
    0.57
     vidéo
    0.57
    хьтан
    0.54
     CCTV
    0.51
     Video
    0.50
    ">//
    0.50
     vídeo
    0.50
     distanciation
    0.50
     recorded
    0.49
    Activations Density 0.499%

    No Known Activations