© 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. 22-GEMMASCOPE-RES-16K
    11. 8561
    Prev
    Next
    INDEX
    Explanations

    references to streaming media and related services

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

    Streaming services and online video

    np_acts-logits-general · gemini-2.0-flash

    streaming movies and shows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Välislingid
    -0.64
    oplasty
    -0.57
     IRC
    -0.55
     betweenstory
    -0.54
    abilia
    -0.53
    cleros
    -0.52
    berdayakan
    -0.51
     engraver
    -0.51
    fotograf
    -0.50
    Γ
    -0.50
    POSITIVE LOGITS
     streaming
    1.51
     Netflix
    1.29
     Streaming
    1.25
    Streaming
    1.14
     stream
    1.14
     streamed
    1.11
    streaming
    1.10
    Netflix
    1.10
     streamer
    1.09
     STREAM
    1.05
    Activations Density 0.126%

    No Known Activations