© 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. 5593
    Prev
    Next
    INDEX
    Explanations

    instances of the word "before" followed by varying degrees of context

    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
     récents
    -0.46
     partielle
    -0.42
     Tourisme
    -0.41
     culturelles
    -0.40
     africains
    -0.39
     campanha
    -0.39
     residencial
    -0.38
     touristique
    -0.38
     eiland
    -0.37
     oignons
    -0.37
    POSITIVE LOGITS
     before
    1.80
    before
    1.75
    Before
    1.57
     Before
    1.56
     BEFORE
    1.48
    BEFORE
    1.46
     sebelum
    1.30
     antes
    1.27
     før
    1.21
     înainte
    1.19
    Activations Density 0.137%

    No Known Activations