© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13014
    Prev
    Next
    INDEX
    Explanations

    scientific concepts related to chemical properties and experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (“
    -0.63
     roughly
    -0.57
     ("
    -0.56
     literally
    -0.56
    rably
    -0.56
    iastes
    -0.54
    ibley
    -0.54
    *)((
    -0.54
    thaler
    -0.53
    πισ
    -0.53
    POSITIVE LOGITS
     equipments
    0.67
     respectivamente
    0.66
     AssemblyTitle
    0.66
     respectivement
    0.64
    DOCTYPE
    0.63
     dolayı
    0.62
     pinulongan
    0.59
    MessageTagHelper
    0.57
     می‌باشد
    0.57
    RegressionTest
    0.56
    Activations Density 1.701%

    No Known Activations