© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 76292
    Prev
    Next
    INDEX
    Explanations

    feedback, suggestions, and criticisms labeled as constructive

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

    constructive behaviour, comments, criticism, suggestions, trust, fraud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     novios
    -0.50
     méri
    -0.48
    colgante
    -0.46
     Irán
    -0.44
     voici
    -0.43
     Ewig
    -0.43
     Keuangan
    -0.42
    tvguidetime
    -0.42
     Polri
    -0.41
     rique
    -0.41
    POSITIVE LOGITS
     constructive
    1.96
     Constru
    1.60
    constru
    1.48
    Constru
    1.41
     constru
    1.39
     constructi
    1.11
     konstruk
    1.09
     конструк
    1.02
     construc
    0.95
    tructive
    0.93
    Activations Density 0.006%

    No Known Activations