© 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-2-9B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12622
    Prev
    Next
    INDEX
    Explanations

    instances of the word "complete" and variations related to completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     userSchema
    -0.57
    yargs
    -0.53
     rétro
    -0.52
     isLoading
    -0.51
    asztok
    -0.51
     UserDao
    -0.51
     senhor
    -0.50
     newUser
    -0.50
    SEGUIR
    -0.50
     senhora
    -0.49
    POSITIVE LOGITS
     completed
    1.19
     completion
    1.18
    complete
    1.18
     Complete
    1.16
    completed
    1.14
    Complete
    1.14
     Completion
    1.14
     complete
    1.13
     completes
    1.12
     COMPLETE
    1.09
    Activations Density 0.058%

    No Known Activations