© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104736
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and functions related to piecewise definitions or discrete variables

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

    Mathematical subscript indices, particularly "i", appearing in scientific or computational notation to denote specific elements in sequences, vectors, or coordinate positions.

    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
     برانيه
    -0.48
    APOLIS
    -0.31
     матери
    -0.30
     tartalomajánló
    -0.30
    Objetivo
    -0.30
    PHeader
    -0.29
    tanleria
    -0.29
    Personendaten
    -0.29
    deckung
    -0.28
     greu
    -0.28
    POSITIVE LOGITS
    writeFieldEnd
    0.54
    MessageTagHelper
    0.53
    Erreferentziak
    0.53
    Autoritní
    0.52
    Diweddarwch
    0.51
    
    0.51
    osoba
    0.50
     geïsole
    0.49
    DockStyle
    0.48
    Personensuche
    0.48
    Activations Density 0.149%

    No Known Activations