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. 6062
    Prev
    Next
    INDEX
    Explanations

    the word "despite" and variations of it, often indicating a contrast or acknowledgment of challenges

    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
     ldc
    -0.40
    jsonwebtoken
    -0.40
     miro
    -0.37
     JsonObject
    -0.37
     Humber
    -0.37
    下一个
    -0.37
     rook
    -0.37
    Русский
    -0.37
     passe
    -0.37
     principal
    -0.37
    POSITIVE LOGITS
     despite
    1.10
    ostante
    1.03
    despite
    1.01
     Despite
    1.00
    Despite
    0.95
     nonostante
    0.95
     malgré
    0.87
     trotz
    0.86
     Malgré
    0.82
     pesar
    0.81
    Activations Density 0.146%

    No Known Activations