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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9473
    Prev
    Next
    INDEX
    Explanations

    statements that indicate contrast or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "but," "actually," or "Q"

    np_acts-logits-general · gemini-2.0-flash

    but actually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.74
    はじめに
    -0.60
    MigrationBuilder
    -0.59
    Спољашње
    -0.58
    queryInterface
    -0.58
    AddTagHelper
    -0.56
    GEBURTS
    -0.55
     propOrder
    -0.52
    関連項目
    -0.49
    aarrggbb
    -0.49
    POSITIVE LOGITS
     actually
    1.74
    actually
    1.61
     Actually
    1.57
    Actually
    1.51
     ACTUALLY
    1.29
    实际上
    1.28
    実は
    1.24
    実際
    1.22
    其实是
    1.21
    其实
    1.21
    Activations Density 0.318%

    No Known Activations