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. 0-GEMMASCOPE-RES-16K
    6. 6807
    Prev
    Next
    INDEX
    Explanations

    instances of the word "completing" or its variations as well as other forms of completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 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
    TypedDataSet
    -0.90
    Xna
    -0.74
    matchCondition
    -0.67
     dépens
    -0.67
     Xunit
    -0.67
     exodus
    -0.67
     sostanze
    -0.66
     exud
    -0.65
    WebVitals
    -0.65
     Miocene
    -0.65
    POSITIVE LOGITS
     completing
    3.65
     completed
    3.63
     completion
    3.61
     completes
    3.48
     complete
    3.36
     Completing
    3.30
    Comple
    3.29
     comple
    3.25
    complete
    3.20
     Completion
    3.17
    Activations Density 0.083%

    No Known Activations