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. 21-GEMMASCOPE-RES-16K
    6. 7103
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with conflict and struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.76
    :✨
    -0.71
    CloseOperation
    -0.69
     мәгълү
    -0.67
     Roskov
    -0.65
     فريبيس
    -0.63
     للاسماء
    -0.62
    ]")]
    -0.60
    rolex
    -0.59
    atimes
    -0.58
    POSITIVE LOGITS
     battles
    1.03
     fight
    1.01
     fought
    1.00
    fight
    1.00
     fights
    0.99
     Fight
    0.87
     against
    0.86
    fights
    0.86
     FIGHT
    0.86
     Fighting
    0.81
    Activations Density 0.061%

    No Known Activations