© 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. 6855
    Prev
    Next
    INDEX
    Explanations

    informal expressions and personal anecdotes related to writing and creative processes

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

    Expressing politeness, apologies, or gratitude

    np_acts-logits-general · gemini-2.0-flash

    hope, sorry, apologies or enjoyment

    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
     betweenstory
    -0.81
    RenderAtEndOf
    -0.77
    Personendaten
    -0.68
     AssemblyTitle
    -0.66
    DispatchToProps
    -0.63
    AddField
    -0.62
    าสตร์
    -0.59
     smtplib
    -0.58
    PhysRevLett
    -0.58
     فريبيس
    -0.56
    POSITIVE LOGITS
     hope
    1.62
    Enjoy
    1.33
     Enjoy
    1.33
     Hope
    1.29
    Hope
    1.29
    hope
    1.22
     enjoy
    1.21
     apologies
    1.21
     sorry
    1.20
    Apologies
    1.19
    Activations Density 0.389%

    No Known Activations