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. 7378
    Prev
    Next
    INDEX
    Explanations

    references to newspapers and related publishing terms

    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
    LayoutConstraint
    -0.47
    NewGuid
    -0.41
     ideal
    -0.41
     Chore
    -0.40
     Sumer
    -0.40
     Rumi
    -0.39
     Juno
    -0.38
    ideal
    -0.38
    cute
    -0.38
    IContainer
    -0.37
    POSITIVE LOGITS
     newspaper
    1.20
     newspapers
    1.09
     Newspaper
    1.00
    Newspaper
    0.99
    newspaper
    0.97
     Newspapers
    0.95
    报纸
    0.85
     journaux
    0.81
     periódico
    0.77
     Zeitung
    0.71
    Activations Density 0.037%

    No Known Activations