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. 13-GEMMASCOPE-RES-16K
    6. 9009
    Prev
    Next
    INDEX
    Explanations

    layout and UI component elements in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verifyException
    -0.62
    MemoryWarning
    -0.52
    SqlSession
    -0.52
     <<<<<<<<<<<<<<
    -0.51
    himu
    -0.48
    SQLiteDatabase
    -0.48
     theo
    -0.47
     BoxDecoration
    -0.46
    ApiOperation
    -0.46
    makeConstraints
    -0.46
    POSITIVE LOGITS
     createState
    1.00
     ſmall
    0.90
     pleaſure
    0.86
     ſtate
    0.83
     houſe
    0.82
     itſelf
    0.81
     ſche
    0.80
     greateſt
    0.78
    ſelves
    0.77
     fevere
    0.77
    Activations Density 0.003%

    No Known Activations