Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 9636
    Prev
    Next
    INDEX
    Explanations

    the concept of "uniformity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.61
    Personensuche
    -0.57
    Datuak
    -0.56
     فريبيس
    -0.55
    RunWith
    -0.52
     AssemblyCulture
    -0.51
     للمعارف
    -0.50
    Geplaatst
    -0.50
    RectangleBorder
    -0.49
    RTLU
    -0.48
    POSITIVE LOGITS
     unified
    1.09
     uniform
    1.08
    uniform
    1.03
     united
    0.99
     unite
    0.97
    unified
    0.97
     synchronized
    0.96
     synchronization
    0.94
     unify
    0.91
     synchronize
    0.91
    Activations Density 0.219%

    No Known Activations