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. 73676
    Prev
    Next
    INDEX
    Explanations

    elements related to software user interface components

    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
    AddTagHelper
    -0.66
    yelitis
    -0.48
    datum
    -0.48
    навли
    -0.47
     contact
    -0.47
     Wikiseite
    -0.46
     Kontakt
    -0.45
    picasso
    -0.45
    contact
    -0.45
     datum
    -0.44
    POSITIVE LOGITS
    menuStrip
    1.22
    JMenuBar
    0.67
    menubar
    0.63
    MenuBar
    0.61
    menuBar
    0.57
    principalColumn
    0.52
    XtraBars
    0.45
    centralwidget
    0.43
    DockStyle
    0.42
    OptionsMenu
    0.42
    Activations Density 0.000%

    No Known Activations