© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 98922
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "video"

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

    video cameras, games, and footage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mijne
    -0.57
     trouw
    -0.51
     oorsp
    -0.44
     leeftijd
    -0.42
     inferiore
    -0.42
    มาะ
    -0.41
     helft
    -0.40
     çat
    -0.40
     natuurlijke
    -0.40
     geluk
    -0.40
    POSITIVE LOGITS
     video
    1.86
     Video
    1.80
    Video
    1.70
    video
    1.65
     VIDEO
    1.53
     videos
    1.42
     vidéo
    1.37
     Videos
    1.34
    VIDEO
    1.32
     Vide
    1.26
    Activations Density 0.009%

    No Known Activations