© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4464
    Prev
    Next
    INDEX
    Explanations

    terms related to pathogens and their environmental interactions

    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
    ary
    -1.34
    logical
    -1.15
    ful
    -1.09
    ual
    -0.93
    ential
    -0.90
    ish
    -0.90
    ulent
    -0.88
    ous
    -0.87
    ARY
    -0.86
    ceutical
    -0.84
    POSITIVE LOGITS
    fulness
    0.65
    ually
    0.59
    ously
    0.57
     BrowserModule
    0.52
    ../../../
    0.50
    ExtendWith
    0.44
    ically
    0.43
    fully
    0.42
     SwiftUI
    0.41
    ably
    0.41
    Activations Density 0.725%

    No Known Activations