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. 10909
    Prev
    Next
    INDEX
    Explanations

    references to exceptional food and culinary experiences

    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
     snow
    -0.42
     ski
    -0.40
     winter
    -0.39
     trigo
    -0.39
     kentang
    -0.38
     ски
    -0.35
     Niedersachsen
    -0.35
     Canterbury
    -0.35
     Loch
    -0.35
     Winter
    -0.34
    POSITIVE LOGITS
     coconut
    1.16
    coconut
    1.08
     Coconut
    1.05
     tropical
    1.04
    Coconut
    1.03
    Tropical
    0.99
     Tropical
    0.98
     kokos
    0.98
    tropical
    0.93
     palm
    0.91
    Activations Density 0.306%

    No Known Activations