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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12714
    Prev
    Next
    INDEX
    Explanations

    phrases related to completion or finishing tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    completion or completing something

    np_acts-logits-general · gemini-2.0-flash

    acts of completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.55
     userSchema
    -0.52
    writerow
    -0.48
    Véxase
    -0.46
     billboards
    -0.45
     Bors
    -0.45
     Jurí
    -0.45
     jurídico
    -0.43
     säga
    -0.43
     kolye
    -0.42
    POSITIVE LOGITS
    completed
    1.15
     completed
    1.13
     completion
    1.10
     Completion
    1.09
    Completed
    1.05
     Completed
    1.05
     completing
    1.05
     Complete
    1.04
     completes
    1.04
    complete
    1.03
    Activations Density 0.106%

    No Known Activations