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. 23-GEMMASCOPE-RES-131K
    6. 23180
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical user interface layout specifications

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sekali
    -0.37
    ño
    -0.35
     пара
    -0.35
     Gruppe
    -0.35
     العق
    -0.35
     сел
    -0.34
    welijk
    -0.33
     once
    -0.33
    voces
    -0.33
    ăsp
    -0.32
    POSITIVE LOGITS
    __(/*!
    0.51
     IBOutlet
    0.50
     resourceCulture
    0.50
     CreateTagHelper
    0.50
    GOTREF
    0.49
    PerformLayout
    0.48
     AssemblyTitle
    0.48
    ContentAlignment
    0.47
    WillAppear
    0.47
     Autorizaciones
    0.47
    Activations Density 0.021%

    No Known Activations