© 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
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6533
    Prev
    Next
    INDEX
    Explanations

    references to specific events or campaigns, particularly those involving Tuesdays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     third
    -0.58
    Fourth
    -0.57
     Fourth
    -0.57
     Third
    -0.56
    Third
    -0.56
    third
    -0.56
     MMM
    -0.56
    第四
    -0.55
     fourth
    -0.54
     Thirdly
    -0.54
    POSITIVE LOGITS
     Tuesday
    1.35
    Tuesday
    1.23
     TUESDAY
    1.02
    tuesday
    1.01
     tuesday
    0.99
     Selasa
    0.96
     Dienstag
    0.94
     Tuesdays
    0.93
    TUESDAY
    0.92
     martes
    0.91
    Activations Density 0.523%

    No Known Activations