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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1122
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements and mathematical symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشارکت‌کنندگان
    -0.55
    RegressionTest
    -0.55
    stdc
    -0.54
     core
    -0.52
     
    -0.51
     Del
    -0.51
     lenker
    -0.50
    SuspendLayout
    -0.49
     hit
    -0.46
     a
    -0.46
    POSITIVE LOGITS
     fubject
    0.86
     myſelf
    0.83
     pleaſure
    0.79
     Houſe
    0.73
     Anſ
    0.73
     utafitiHapana
    0.72
     GIPHY
    0.70
     deſt
    0.70
     ſever
    0.70
     neceſſ
    0.70
    Activations Density 2.637%

    No Known Activations