© 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. 3-GEMMASCOPE-RES-16K
    11. 9037
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a small quantity or slight degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bø
    -0.43
     sederhana
    -0.42
    しゃれ
    -0.42
    krank
    -0.41
     antiguo
    -0.41
    old
    -0.39
    PHOTOS
    -0.38
    యు
    -0.38
     nélkül
    -0.37
     übrigen
    -0.37
    POSITIVE LOGITS
    aarrggbb
    1.11
    parsedMessage
    1.04
    +#+#
    0.97
    FieldBuilder
    0.96
    hasNext
    0.94
    PhysRev
    0.93
    AccessorTable
    0.93
    ViewFeatures
    0.89
    structors
    0.89
    migrationBuilder
    0.87
    Activations Density 0.102%

    No Known Activations