© 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. 5646
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to educational funding and program changes

    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
     our
    -0.98
     Our
    -0.84
    Our
    -0.81
     ourselves
    -0.78
    是我们
    -0.75
     nostre
    -0.74
     OUR
    -0.73
     ours
    -0.68
     nuestro
    -0.66
     우리
    -0.66
    POSITIVE LOGITS
     Officials
    0.90
    Officials
    0.85
     officials
    0.69
     Asked
    0.61
    Asked
    0.61
     etwa
    0.60
    OGND
    0.59
    About
    0.59
     About
    0.57
    But
    0.56
    Activations Density 0.268%

    No Known Activations