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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5325
    Prev
    Next
    INDEX
    Explanations

    terms related to disease outbreaks and ecological 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
    ConstraintMaker
    -0.42
     épaules
    -0.38
     المعرف
    -0.37
    internalType
    -0.36
    stateMutability
    -0.35
    extAlignment
    -0.35
    colage
    -0.34
    Referensi
    -0.32
     rêves
    -0.32
     arvio
    -0.32
    POSITIVE LOGITS
     infection
    1.80
     infected
    1.77
     epidemics
    1.76
     infect
    1.75
     epidemic
    1.73
     virus
    1.69
     infectious
    1.68
     Infection
    1.66
     infections
    1.64
     infecting
    1.63
    Activations Density 0.977%

    No Known Activations