© 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. 106278
    Prev
    Next
    INDEX
    Explanations

    terms related to mental processes and emotional awareness

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

    Words related to mental processes and cognition (thoughts, thinking, cognitive, mind) that appear in psychological, medical, spiritual, and educational contexts.

    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
    AddTagHelper
    -0.50
     <>",
    -0.48
    localctx
    -0.44
    AndEndTag
    -0.43
     IERC
    -0.43
    wapV
    -0.43
     excelentes
    -0.42
    lichkeit
    -0.42
     autorytatywna
    -0.40
     zweifel
    -0.40
    POSITIVE LOGITS
     thoughts
    0.65
     pensieri
    0.61
    thoughts
    0.57
     Thoughts
    0.54
     pensamientos
    0.52
    Thoughts
    0.50
     Thought
    0.47
     mental
    0.45
     THOUGHTS
    0.45
     formation
    0.44
    Activations Density 0.017%

    No Known Activations