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. 5-GEMMASCOPE-RES-16K
    6. 11948
    Prev
    Next
    INDEX
    Explanations

    mentions of battles or conflict-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fins
    -0.79
    exels
    -0.75
     firebaseConfig
    -0.73
    --
    
    -0.71
    _
    
    -0.71
    stalt
    -0.71
    ]))
    
    -0.70
    MatInputModule
    -0.70
    ++
    
    -0.70
    LEncoder
    -0.68
    POSITIVE LOGITS
     battle
    1.96
     Battle
    1.92
     BATTLE
    1.80
    Battle
    1.77
     battles
    1.74
    battle
    1.74
    BATTLE
    1.70
     Battles
    1.61
     battled
    1.49
    Battles
    1.48
    Activations Density 0.035%

    No Known Activations