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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8333
    Prev
    Next
    INDEX
    Explanations

    words associated with financial transactions and responsibilities

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

    project completion or commencement

    np_acts-logits-general · gemini-2.0-flash

    project completion and finalization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    脚注の使い方
    -0.58
     دیکھیے
    -0.57
    neurial
    -0.51
    tvguidetime
    -0.51
     chi̍t
    -0.51
     فريبيس
    -0.51
    closedir
    -0.51
     pinulongan
    -0.50
    soort
    -0.50
     estekak
    -0.49
    POSITIVE LOGITS
     completion
    1.11
     Completion
    1.04
     completed
    0.98
     commissioning
    0.94
    completion
    0.91
    Completion
    0.89
     commencement
    0.88
     finalized
    0.86
     Completed
    0.84
     commenced
    0.83
    Activations Density 0.285%

    No Known Activations