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. 12-GEMMASCOPE-RES-16K
    6. 5972
    Prev
    Next
    INDEX
    Explanations

    terms related to central governance or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comets
    -0.91
     Roskov
    -0.83
     Dolom
    -0.80
     Prophets
    -0.79
     Phry
    -0.79
     astronomers
    -0.78
     Kurds
    -0.78
     Ips
    -0.77
     moons
    -0.76
     Trooper
    -0.75
    POSITIVE LOGITS
     Central
    1.40
    Central
    1.30
    CENTRAL
    1.20
     CENTRAL
    1.19
     central
    1.15
    central
    1.14
    Datuak
    0.99
     centrales
    0.99
    بوابة
    0.96
     Centra
    0.89
    Activations Density 0.051%

    No Known Activations