© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 12711
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the term "Mat"

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

    words starting with Mat

    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
     nahilalakip
    -0.54
     כול
    -0.50
    eroy
    -0.50
     köl
    -0.47
    horabuena
    -0.46
    >
    -0.45
     glyphicon
    -0.45
     ciudadano
    -0.45
     Económica
    -0.44
     createTime
    -0.43
    POSITIVE LOGITS
     Mat
    2.22
    Mat
    2.09
     mat
    1.91
    mat
    1.66
     MAT
    1.65
    MAT
    1.50
    Matty
    1.35
     Мат
    1.28
     mats
    1.22
     Matti
    1.18
    Activations Density 0.007%

    No Known Activations