© 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. 5682
    Prev
    Next
    INDEX
    Explanations

    interrogative words or phrases, indicating a focus on questions and inquiries

    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
     Vorteil
    -0.53
    HtmlAttribute
    -0.53
    MigrationBuilder
    -0.53
     Plummer
    -0.52
     merci
    -0.51
    SharedCtor
    -0.50
    vara
    -0.50
    ец
    -0.50
     layui
    -0.50
    strcat
    -0.49
    POSITIVE LOGITS
    what
    1.10
     what
    1.09
     combien
    1.06
     mitä
    0.95
     WHAT
    0.95
     WHICH
    0.94
    What
    0.92
     whom
    0.91
     Whom
    0.90
    WHAT
    0.90
    Activations Density 0.207%

    No Known Activations