© 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. 37-GEMMASCOPE-RES-16K
    11. 5144
    Prev
    Next
    INDEX
    Explanations

    references to research processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    distribute
    -0.62
    introduce
    -0.59
    communicate
    -0.58
    migrate
    -0.57
    Autoritní
    -0.57
     distributing
    -0.56
    decorate
    -0.56
     kasarigan
    -0.56
     redistribute
    -0.55
    đầm
    -0.54
    POSITIVE LOGITS
     detection
    0.72
     adaptation
    0.71
     identification
    0.71
     submission
    0.69
     absorption
    0.69
     preservation
    0.69
     determination
    0.67
     estimation
    0.66
     prevention
    0.66
     promotion
    0.66
    Activations Density 2.216%

    No Known Activations