© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 102524
    Prev
    Next
    INDEX
    Explanations

    mentions of California election officials and their statements regarding voter fraud claims

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

    Reporting verbs and phrases that indicate formal responses to claims or allegations, often in legal, political, or official 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
    qtype
    -0.34
    
    -0.34
    тельностью
    -0.32
    ฉ
    -0.31
     spread
    -0.29
     depende
    -0.29
     fű
    -0.29
     exemplaire
    -0.28
    ₨
    -0.28
     aguj
    -0.28
    POSITIVE LOGITS
     nahilalakip
    0.76
     utafitiHapana
    0.75
    Havolalar
    0.65
     linkovi
    0.65
     nakalista
    0.62
    elemField
    0.62
    CompleteListener
    0.60
     CreateTagHelper
    0.60
     kasarigan
    0.59
    әрмәләр
    0.59
    Activations Density 0.230%

    No Known Activations