© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 6998
    Prev
    Next
    INDEX
    Explanations

    phrases that denote rationale or justification for actions or statements

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

    a cause-and-effect relationship

    np_acts-logits-general · gemini-2.0-flash

    introduces explanation or consequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     grà
    -0.53
     owing
    -0.53
     understood
    -0.52
    ajevo
    -0.52
     NSCoder
    -0.51
    telling
    -0.51
    ThroughAttribute
    -0.50
     because
    -0.50
     becau
    -0.50
    Vidite
    -0.50
    POSITIVE LOGITS
    あえて
    0.70
    特意
    0.59
    HasForeignKey
    0.56
     daarom
    0.56
     ezért
    0.56
     Daarom
    0.55
    invokeLater
    0.55
    __':
    0.55
     graag
    0.54
     derfor
    0.52
    Activations Density 0.384%

    No Known Activations