© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5192
    Prev
    Next
    INDEX
    Explanations

    terminology related to experimental protocols and animal care in scientific studies

    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
     geſch
    -0.70
     Geiſt
    -0.68
     verſch
    -0.66
     laſſen
    -0.64
    ſchaft
    -0.63
     beſch
    -0.60
     vooz
    -0.59
     müſſen
    -0.59
    TargetException
    -0.57
     wiſſen
    -0.57
    POSITIVE LOGITS
     and
    2.80
    และ
    1.15
     и
    1.05
    性和
    1.01
     và
    0.99
    子和
    0.95
     और
    0.95
    and
    0.90
     και
    0.89
    力和
    0.88
    Activations Density 22.209%

    No Known Activations