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. 130971
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements related to scientific experiments

    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
     OSD
    -0.51
     DCT
    -0.50
     吋
    -0.49
     fuzz
    -0.48
     BBB
    -0.47
     OSM
    -0.46
     LHS
    -0.46
    naf
    -0.46
    FontOfSize
    -0.45
     DST
    -0.45
    POSITIVE LOGITS
    eseorang
    0.42
     Jerusalén
    0.39
     Verhält
    0.38
     dépos
    0.36
     musicales
    0.36
    interprétation
    0.36
     gerecht
    0.36
     dépôt
    0.35
    的一种
    0.35
     fallu
    0.35
    Activations Density 0.150%

    No Known Activations