© 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. 5-GEMMASCOPE-RES-16K
    11. 13879
    Prev
    Next
    INDEX
    Explanations

    attributes and their corresponding values in markup or programming structures

    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
    WEBPACK
    -0.55
    ValueStyle
    -0.51
     Dau
    -0.51
    yue
    -0.48
     coeur
    -0.48
    naires
    -0.48
    rante
    -0.47
    kler
    -0.46
    Balan
    -0.46
     heart
    -0.45
    POSITIVE LOGITS
     htmlFor
    1.43
    migrationBuilder
    0.95
     InputDecoration
    0.89
    awaiter
    0.78
    MigrationBuilder
    0.74
     ModelExpression
    0.73
     propOrder
    0.72
    MessageTagHelper
    0.71
    baomidou
    0.71
     IndexPath
    0.70
    Activations Density 0.033%

    No Known Activations