© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 59163
    Prev
    Next
    INDEX
    Explanations

    instances of the sequence "AG" and its variations in the context of genetic sequences or biochemical terms

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

    kag, AG, CAG, AGG

    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
     Franken
    -0.41
    o
    -0.40
     Goodwin
    -0.40
     Hartman
    -0.39
     Teo
    -0.39
     Longo
    -0.39
    ✎
    -0.38
     Dutta
    -0.38
     Stevenson
    -0.37
    ▶
    -0.37
    POSITIVE LOGITS
     Kag
    2.48
    Kag
    2.23
    kag
    1.90
     kag
    1.88
     Cag
    1.11
     CAG
    0.95
     Kah
    0.91
    CAG
    0.83
    Kah
    0.82
     cag
    0.81
    Activations Density 0.003%

    No Known Activations