© 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. 105983
    Prev
    Next
    INDEX
    Explanations

    indicators of unprofessional or inappropriate workplace conduct

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

    Line breaks that occur mid-sentence in formal legal or technical documents, where text continues on the next line without respecting natural sentence boundaries.

    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
    iſen
    -1.21
     ब्रेकडाउन
    -1.16
    majánló
    -1.16
     queſta
    -1.13
     ſind
    -1.13
     ſei
    -1.07
    niſſe
    -1.07
     ſein
    -1.07
     zwiſchen
    -1.07
    ſſung
    -1.05
    POSITIVE LOGITS
    \
    0.63
    0
    0.61
    ↵↵
    0.54
    .
    0.53
    {
    0.52
    ;
    0.51
    s
    0.50
    4
    0.50
        
    0.49
    0.49
    Activations Density 0.063%

    No Known Activations