© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6382
    Prev
    Next
    INDEX
    Explanations

    geographical references and mentions of universities, particularly in California

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

    US state names.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    InstrumentedTest
    -0.53
     noDo
    -0.44
    writeFieldEnd
    -0.44
     citada
    -0.41
    Bigg
    -0.41
    Clik
    -0.41
     recevrez
    -0.40
     Durchmesser
    -0.40
     Begründung
    -0.40
    gruppo
    -0.40
    POSITIVE LOGITS
     Maryland
    1.01
     Virginia
    1.00
     Pennsylvania
    0.98
     Florida
    0.95
     Illinois
    0.93
    Maryland
    0.92
     Missouri
    0.91
    Virginia
    0.91
     Connecticut
    0.91
     California
    0.89
    Activations Density 0.189%

    No Known Activations