© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10719
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "video" in different contexts

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

    "video" preceding other words

    np_acts-logits-general · gemini-2.0-flash

    video games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zusetzen
    -0.34
     vyu
    -0.33
    istung
    -0.33
    AZIONI
    -0.31
     costitu
    -0.31
     casal
    -0.30
     strukt
    -0.30
    ']))
    -0.30
     tomber
    -0.29
     álla
    -0.28
    POSITIVE LOGITS
     Video
    0.78
    Video
    0.77
     snippetHide
    0.71
    Vide
    0.71
    tape
    0.70
    Vid
    0.68
     Vide
    0.66
    RenderAtEndOf
    0.65
     conferencing
    0.63
     VIDE
    0.63
    Activations Density 0.100%

    No Known Activations