© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 13379
    Prev
    Next
    INDEX
    Explanations

    information about live broadcasts or events

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

    About "live" or "being broadcast"

    np_acts-logits-general · gemini-2.0-flash

    live broadcast or stream

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GetEnumerator
    -0.52
     verwijderen
    -0.45
     InputDecoration
    -0.45
     vaih
    -0.44
     gustos
    -0.44
     جه
    -0.43
    niosek
    -0.43
     établie
    -0.43
    Clik
    -0.42
    ]")]
    -0.42
    POSITIVE LOGITS
     live
    1.65
     livestream
    1.60
     Live
    1.36
     streamed
    1.35
     streaming
    1.34
    Live
    1.30
    live
    1.28
     LIVE
    1.25
     broadcast
    1.25
    LIVE
    1.18
    Activations Density 0.191%

    No Known Activations