Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1599
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about electronic devices

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

    Television or set-top box related content

    np_acts-logits-general · gemini-2.0-flash

    television and broadcast channels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Exactos
    -0.51
    otechnical
    -0.47
     civile
    -0.47
     tour
    -0.45
     expon
    -0.45
    idente
    -0.45
    著
    -0.44
     chambers
    -0.44
     toured
    -0.44
    Rapp
    -0.43
    POSITIVE LOGITS
    клопе
    0.85
     Television
    0.81
     TV
    0.81
    ValueStyle
    0.81
     television
    0.78
     OFDb
    0.76
     Netflix
    0.75
     IPTV
    0.75
     households
    0.75
    Television
    0.73
    Activations Density 0.355%

    No Known Activations