Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9717
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical tensions and military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovell
    -0.39
     gustó
    -0.36
    참고
    -0.35
    PhysRevLett
    -0.35
     Tong
    -0.34
     sultan
    -0.34
     boyut
    -0.34
     læng
    -0.33
     Kruse
    -0.33
     Hammond
    -0.33
    POSITIVE LOGITS
     Ukrainian
    1.84
     Ukraine
    1.80
     Ukrainians
    1.65
    Ukrainian
    1.55
     Kyiv
    1.50
     ukrain
    1.49
     Ukra
    1.48
    Ukraine
    1.48
     ukra
    1.43
     Ukrain
    1.40
    Activations Density 0.153%

    No Known Activations