© 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. 18-GEMMASCOPE-RES-16K
    11. 14877
    Prev
    Next
    INDEX
    Explanations

    phrases related to news and television broadcasts

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

    Television or broadcasting related content

    np_acts-logits-general · gemini-2.0-flash

    local news broadcasting

    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
     CreateTagHelper
    -0.52
    ebook
    -0.49
    AddTagHelper
    -0.47
    Etsy
    -0.45
    İstinadlar
    -0.45
     nahilalakip
    -0.45
     cuir
    -0.44
     GitHub
    -0.43
     hardcover
    -0.43
     Schützen
    -0.43
    POSITIVE LOGITS
     broadcast
    1.57
     television
    1.49
     TV
    1.45
     broadcasting
    1.44
     Broadcast
    1.36
     broadcasts
    1.35
     Television
    1.34
     Broadcasting
    1.33
    TV
    1.32
     broadcaster
    1.32
    Activations Density 0.328%

    No Known Activations