© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9093
    Prev
    Next
    INDEX
    Explanations

    terms related to sponsorship and sponsorship activities

    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
     bege
    -0.63
     Gell
    -0.59
     thế
    -0.55
     "'";
    -0.55
    uerre
    -0.54
    הערות
    -0.53
    LikeLike
    -0.53
    Joh
    -0.52
    ียบ
    -0.52
     
    -0.52
    POSITIVE LOGITS
     sponsor
    3.57
     sponsors
    3.48
     Sponsor
    3.23
     sponsorship
    3.22
     Sponsors
    3.18
     sponsored
    3.12
     sponsoring
    3.02
    Sponsor
    3.00
    sponsor
    2.97
     SPONS
    2.90
    Activations Density 0.057%

    No Known Activations