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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 3062
    Prev
    Next
    INDEX
    Explanations

    words that begin with "ex" or pertain to excessive or extraordinary conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ppelin
    -0.97
     numberOfRows
    -0.95
     useParams
    -0.93
    AnimationsModule
    -0.88
    ANDUM
    -0.87
    mobileqq
    -0.86
    BRD
    -0.85
    rillation
    -0.85
    httphttps
    -0.83
    LabelTagHelper
    -0.82
    POSITIVE LOGITS
    ex
    1.45
     Ex
    1.37
    Ex
    1.32
     EX
    1.31
     ex
    1.29
    EX
    1.25
    exc
    1.01
     Exc
    0.96
     EXPO
    0.94
     exc
    0.93
    Activations Density 0.222%

    No Known Activations