© 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. 15262
    Prev
    Next
    INDEX
    Explanations

    financial figures and economic data related to national debt and expenditures

    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
     Millionen
    -0.58
    Архівовано
    -0.50
     millones
    -0.49
     classNames
    -0.48
    OMI
    -0.48
    ்கு
    -0.48
     millions
    -0.47
     OMIT
    -0.47
    forChild
    -0.46
     مليون
    -0.46
    POSITIVE LOGITS
     trillion
    1.05
    tri
    0.89
     tri
    0.88
     Tri
    0.80
    Tril
    0.79
     tril
    0.73
    djangoproject
    0.69
    Tri
    0.68
    trn
    0.66
    rotum
    0.64
    Activations Density 0.215%

    No Known Activations