Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2113
    Prev
    Next
    INDEX
    Explanations

    terms related to "universal" concepts or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pert
    -0.75
     Naughty
    -0.69
    })));
    -0.67
    ++){
    
    -0.66
    ])));
    -0.66
    dts
    -0.64
     Sumter
    -0.64
    lty
    -0.64
    Alk
    -0.63
     IConfiguration
    -0.63
    POSITIVE LOGITS
     Universal
    1.01
     Universe
    1.00
     studios
    0.96
    universal
    0.94
    Universal
    0.93
     universal
    0.92
    UNIVERS
    0.91
     universe
    0.90
     universality
    0.90
     universale
    0.89
    Activations Density 0.089%

    No Known Activations