© 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. 37-GEMMASCOPE-RES-16K
    11. 7921
    Prev
    Next
    INDEX
    Explanations

    key concepts related to dishonor and various medical conditions, particularly focusing on specific terms associated with health issues and their treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     programme
    -0.76
    programme
    -0.74
     programmes
    -0.72
    Programme
    -0.67
     Programmes
    -0.66
     personalise
    -0.65
     PROGRAMME
    -0.65
     analysing
    -0.64
     centralised
    -0.63
     Programme
    -0.62
    POSITIVE LOGITS
     armor
    0.88
     labor
    0.88
     fiber
    0.87
     honor
    0.82
     theater
    0.81
     honors
    0.78
     honored
    0.75
     Savior
    0.75
     harbor
    0.75
     mold
    0.75
    Activations Density 0.434%

    No Known Activations