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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11341
    Prev
    Next
    INDEX
    Explanations

    elements related to user management and admin functionalities in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atterns
    -0.32
     consumers
    -0.30
     stayed
    -0.30
     exp
    -0.29
     sesame
    -0.29
    ResponseWriter
    -0.29
     prop
    -0.28
     app
    -0.28
     CONSUMER
    -0.28
    NSMutableArray
    -0.28
    POSITIVE LOGITS
    setVerticalGroup
    0.71
     فريبيس
    0.65
    PerformLayout
    0.63
    énario
    0.60
    Tikang
    0.58
    Autoritní
    0.57
    IUrlHelper
    0.57
    ロウィン
    0.57
     Cæsar
    0.56
     تضيفلها
    0.56
    Activations Density 0.041%

    No Known Activations