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. 34-GEMMASCOPE-RES-16K
    6. 11507
    Prev
    Next
    INDEX
    Explanations

    references to the Congo and associated military and political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obrador
    -0.37
     sarili
    -0.35
    </caption>
    -0.35
    __()
    -0.32
     Saab
    -0.32
     TOPICS
    -0.31
    彩
    -0.31
     Nors
    -0.31
    ruptedException
    -0.31
     POSTAGE
    -0.31
    POSITIVE LOGITS
     Rwanda
    0.92
    Rwanda
    0.84
     Rwand
    0.83
     Kigali
    0.80
     ujednoznacz
    0.61
     Genocide
    0.58
     Kag
    0.57
     Ruh
    0.57
     Burundi
    0.56
     समीक्षाओं
    0.55
    Activations Density 0.172%

    No Known Activations