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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53678
    Prev
    Next
    INDEX
    Explanations

    terms related to synergy and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -0.38
     Republik
    -0.37
     "/
    -0.36
    ("
    -0.35
    Read
    -0.34
     날
    -0.34
    Bbb
    -0.32
     getObject
    -0.32
    ọc
    -0.32
    ****************
    -0.32
    POSITIVE LOGITS
     Synergy
    1.22
     synergy
    1.20
     synergies
    1.16
     syner
    1.02
     Syner
    1.01
     synerg
    1.00
     synergistic
    0.96
     amizade
    0.79
     autorytatywna
    0.78
     parceria
    0.76
    Activations Density 0.010%

    No Known Activations