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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90033
    Prev
    Next
    INDEX
    Explanations

    references to video and visual media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.62
     trouw
    -0.50
    approche
    -0.49
     zijne
    -0.46
     çat
    -0.46
     asiática
    -0.46
    she
    -0.45
     Constitucional
    -0.44
     geluk
    -0.44
     ouder
    -0.44
    POSITIVE LOGITS
     Video
    1.18
    Video
    1.16
     video
    1.14
    video
    1.07
     VIDEO
    1.00
     Videos
    0.90
    VIDEO
    0.89
     videos
    0.86
    存于互联网档案馆
    0.84
     Vide
    0.82
    Activations Density 0.008%

    No Known Activations