© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105954
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to rights and responsibilities

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

    Technical or specialized terminology that appears in formal documents such as legal opinions, academic papers, or political commentary, often serving as key terms that complete important concepts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     en
    -0.34
     inv
    -0.33
     den
    -0.33
    UnusedPrivate
    -0.32
    textLabel
    -0.32
     gy
    -0.32
     hun
    -0.32
    HOY
    -0.31
    VertexAttrib
    -0.31
     bâ
    -0.31
    POSITIVE LOGITS
     للاسماء
    0.58
    rungsseite
    0.58
    逆に
    0.54
     propOrder
    0.52
     AssemblyTitle
    0.50
    ftagPool
    0.50
     damska
    0.49
    mybatisplus
    0.49
    VersionUID
    0.49
    /**
    0.48
    Activations Density 0.394%

    No Known Activations