© 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. 2-GEMMASCOPE-RES-16K
    11. 8403
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to metabolites and their applications in cancer research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fenn
    -0.80
     Calvo
    -0.72
    گاب
    -0.69
     ostr
    -0.68
     Dialog
    -0.67
    DbType
    -0.66
     Gale
    -0.66
     FEN
    -0.65
     pathlib
    -0.65
     MatDialog
    -0.64
    POSITIVE LOGITS
     Zwer
    0.75
    __":
    0.73
     مرئيه
    0.72
     colonies
    0.72
     Evansville
    0.71
     Darcy
    0.71
    Lilly
    0.69
    Gos
    0.69
     Parigi
    0.69
     yamaha
    0.68
    Activations Density 7.232%

    No Known Activations