© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14618
    Prev
    Next
    INDEX
    Explanations

    programming related to application context and infrastructure setup

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

    Code-related terms or imports

    np_acts-logits-general · gemini-2.0-flash

    import and LoggerFactory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     kaarangay
    -0.77
     كومونز
    -0.73
    ьаж
    -0.60
     незавершена
    -0.60
    hoeddwyd
    -0.59
    msgTypes
    -0.59
     pinulongan
    -0.59
     يتيمه
    -0.59
     Normdatei
    -0.58
     Autorizaciones
    -0.57
    POSITIVE LOGITS
     Hes
    0.36
    ofan
    0.35
     השת
    0.34
    Ped
    0.34
    grafos
    0.34
    WireFormat
    0.33
     Ped
    0.33
    λογία
    0.33
    yalar
    0.33
    Els
    0.33
    Activations Density 0.159%

    No Known Activations