© 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. 36-GEMMASCOPE-RES-16K
    11. 6652
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research, particularly in the context of screening and evaluating biological samples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.70
    Diweddarwch
    -0.67
    AutoScaleMode
    -0.66
    writeFieldEnd
    -0.59
    ftagPool
    -0.58
    AnchorTagHelper
    -0.55
    хьтан
    -0.51
    EndGlobalSection
    -0.48
     MainAxisSize
    -0.48
    ValueStyle
    -0.47
    POSITIVE LOGITS
     thousands
    3.41
     hundreds
    3.36
    thousands
    2.98
    hundreds
    2.92
     Thousands
    2.86
    Hundreds
    2.84
    Thousands
    2.83
     Hundreds
    2.83
     millions
    2.58
     dozens
    2.52
    Activations Density 1.895%

    No Known Activations