© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 10830
    Prev
    Next
    INDEX
    Explanations

    references to upper and lower parts of various structures or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oas
    -0.56
     eventId
    -0.56
    RSpec
    -0.54
     Inoc
    -0.54
    detectChanges
    -0.54
     Scandal
    -0.53
    eeqa
    -0.53
     pajamas
    -0.51
    folios
    -0.51
    glEnd
    -0.50
    POSITIVE LOGITS
     higher
    1.02
     upper
    1.02
     Upper
    1.01
    Upper
    0.94
    higher
    0.90
    Higher
    0.88
     Higher
    0.88
    upper
    0.85
     UPPER
    0.84
     above
    0.82
    Activations Density 0.355%

    No Known Activations