© 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. 4-GEMMASCOPE-RES-16K
    11. 2697
    Prev
    Next
    INDEX
    Explanations

    information related to premiere dates and airing details of television shows and films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukone
    -0.63
    Diweddarwch
    -0.62
    fjspx
    -0.61
     שוליים
    -0.59
    complexContent
    -0.56
    DeleteBehavior
    -0.55
    phazard
    -0.55
    पया
    -0.54
     zoek
    -0.53
     Taktlose
    -0.53
    POSITIVE LOGITS
     broadcast
    1.17
     aired
    1.10
     premiered
    1.09
     broadcasts
    1.09
     premiere
    1.05
     airing
    1.03
     premieres
    0.98
     broadcasting
    0.96
    premiere
    0.93
    broadcast
    0.93
    Activations Density 0.396%

    No Known Activations