© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3854
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "is" in various forms, emphasizing its usage as a verb or identifier in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unhofer
    -0.61
    émoc
    -0.60
    VersionUID
    -0.53
     éter
    -0.52
    recated
    -0.51
    Einzelnachweise
    -0.50
    Quy
    -0.50
    StackNavigator
    -0.49
     provisoire
    -0.49
     despe
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.79
     незавершена
    0.70
     non
    0.68
    UnusedPrivate
    0.64
     otomatig
    0.64
     kaarangay
    0.62
    非
    0.62
     非
    0.60
    انيف
    0.59
    如果不是
    0.59
    Activations Density 1.158%

    No Known Activations