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-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 16024
    Prev
    Next
    INDEX
    Explanations

    phrases related to control and dominance in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mazioni
    -0.51
     complement
    -0.50
    PLEMENT
    -0.47
    erdan
    -0.47
    continu
    -0.46
    Rat
    -0.46
    målet
    -0.45
    Memo
    -0.45
    CELLANEOUS
    -0.45
     progresso
    -0.45
    POSITIVE LOGITS
     domination
    1.14
     dominance
    1.04
     control
    1.02
     dominion
    1.02
     domina
    0.96
     takeover
    0.95
     Control
    0.95
     Controlling
    0.94
     dominate
    0.93
     controlling
    0.92
    Activations Density 0.328%

    No Known Activations