© 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 EvalsExportsAPI 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. 2613
    Prev
    Next
    INDEX
    Explanations

    verbs and their usage in statements about eligibility and patient populations

    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
    RetentionPolicy
    -0.64
    AnchorStyles
    -0.57
    RTSC
    -0.54
     nahilalakip
    -0.52
    FontOfSize
    -0.48
    TAWA
    -0.47
    PYX
    -0.47
    EDEFAULT
    -0.47
    CloseOperation
    -0.47
    homonymie
    -0.47
    POSITIVE LOGITS
     accommodated
    1.00
     cared
    0.90
     treated
    0.88
     served
    0.87
     educated
    0.79
     protected
    0.78
     serviced
    0.77
     assisted
    0.77
     coached
    0.76
     nurtured
    0.74
    Activations Density 0.813%

    No Known Activations