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. 5-GEMMASCOPE-RES-16K
    6. 14272
    Prev
    Next
    INDEX
    Explanations

    words related to inner and outer measurements or boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atchewan
    -0.87
     againſt
    -0.83
     通販
    -0.82
    RegressionTest
    -0.80
    romyalgia
    -0.78
     ProtoMessage
    -0.75
     propOrder
    -0.74
     Tallahassee
    -0.74
    hésite
    -0.73
     Catalunya
    -0.73
    POSITIVE LOGITS
     inner
    2.06
     Inner
    2.05
    Inner
    1.88
    inner
    1.81
     INNER
    1.79
    INNER
    1.53
     Outer
    1.37
     OUTER
    1.35
     outer
    1.35
    Outer
    1.27
    Activations Density 0.072%

    No Known Activations