© 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. 12-GEMMASCOPE-RES-16K
    11. 9542
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific or medical concepts

    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
    Tabbed
    -0.59
    iels
    -0.51
    }`).
    -0.47
     dipas
    -0.46
     rave
    -0.46
    ondon
    -0.46
    Lac
    -0.46
    gev
    -0.46
    वे
    -0.46
     Islamic
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.90
     feel
    0.78
    featureID
    0.78
    aarrggbb
    0.78
    feel
    0.75
     Feel
    0.73
    PerformLayout
    0.73
    Feels
    0.72
    WithIOException
    0.71
    Felt
    0.70
    Activations Density 0.189%

    No Known Activations