© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5594
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to functions and expressions

    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
    Frida
    -0.81
     Frida
    -0.77
    Spinach
    -0.73
     Spinach
    -0.68
     Richmond
    -0.66
     spinach
    -0.65
     ECS
    -0.65
     Friedman
    -0.65
    Richmond
    -0.65
     McGowan
    -0.60
    POSITIVE LOGITS
     Bronco
    0.67
     Harley
    0.66
     Norton
    0.64
     Jir
    0.63
     bronco
    0.62
     Rodney
    0.61
     McNeil
    0.61
     Kara
    0.61
     Armstrong
    0.60
     Severn
    0.60
    Activations Density 2.092%

    No Known Activations