© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107005
    Prev
    Next
    INDEX
    Explanations

    instances of the word "content" and related terms in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    content assignments and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    +#+#
    -0.58
    她們
    -0.55
     marinho
    -0.52
     automatiques
    -0.51
     queſta
    -0.51
    ishly
    -0.50
    aarrggbb
    -0.49
     vété
    -0.48
    améli
    -0.48
     yoktur
    -0.47
    POSITIVE LOGITS
    content
    0.90
    Content
    0.90
    CONTENT
    0.78
     Content
    0.74
     CONTENT
    0.68
    ContentAlignment
    0.67
    conten
    0.65
    getContent
    0.63
     content
    0.63
     conten
    0.62
    Activations Density 0.012%

    No Known Activations