© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9338
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to networking and network structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "network"

    np_acts-logits-general · gemini-2.0-flash

    network of or network following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mourut
    -0.89
     titolata
    -0.87
     GLS
    -0.86
     meurt
    -0.85
     héro
    -0.85
     feroit
    -0.84
     hâte
    -0.83
     réaliste
    -0.83
     colorés
    -0.82
     abstrait
    -0.82
    POSITIVE LOGITS
     networks
    1.00
     network
    0.91
    Network
    0.80
     Network
    0.79
     networking
    0.76
    networks
    0.75
    Networks
    0.74
    network
    0.73
     Networks
    0.71
     networked
    0.70
    Activations Density 0.093%

    No Known Activations