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. 4847
    Prev
    Next
    INDEX
    Explanations

    instances of the term "victory" and related phrases about success or achievements

    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
     Nass
    -1.08
     оригіналу
    -0.92
    Nass
    -0.84
     Fass
    -0.82
    "?>
    -0.80
     चीज़ों
    -0.79
     Bouch
    -0.78
    iness
    -0.77
     Gass
    -0.76
    expandindo
    -0.76
    POSITIVE LOGITS
    Mixtures
    0.90
     vectorielle
    0.87
     élect
    0.87
    coverage
    0.84
     firent
    0.83
     furent
    0.83
     graphiques
    0.82
     côtes
    0.82
     vectorielles
    0.81
     Cæsar
    0.81
    Activations Density 0.110%

    No Known Activations