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. 411
    Prev
    Next
    INDEX
    Explanations

    references to purchasing and transactions

    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
     Houſe
    -0.82
     esternos
    -0.79
     Anſ
    -0.77
     Мексичка
    -0.76
     المعيارى
    -0.75
    Хьажоргаш
    -0.73
    Belly
    -0.71
    talk
    -0.70
     Reſ
    -0.69
     Theſe
    -0.69
    POSITIVE LOGITS
     upon
    0.68
    maktadır
    0.60
    mektedir
    0.60
     utilizing
    0.59
     utilising
    0.55
     Utilizamos
    0.49
     lorsqu
    0.49
     Upon
    0.49
     UPON
    0.48
     whilst
    0.47
    Activations Density 1.034%

    No Known Activations