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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15085
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to cancer research and treatment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     varandra
    -0.90
     mères
    -0.90
     connus
    -0.89
     chrétiens
    -0.88
     stället
    -0.87
     vägen
    -0.85
     aikaa
    -0.85
     espirituales
    -0.85
     dépens
    -0.84
     avoient
    -0.83
    POSITIVE LOGITS
     product
    0.76
     stuff
    0.72
     data
    0.72
     items
    0.71
     efforts
    0.70
     results
    0.70
     activities
    0.70
     event
    0.70
     situation
    0.69
     portion
    0.69
    Activations Density 1.720%

    No Known Activations