© 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. 38-GEMMASCOPE-RES-16K
    11. 14680
    Prev
    Next
    INDEX
    Explanations

    terms related to infectious diseases and their dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    internalType
    -0.43
    mtliche
    -0.43
    ArrowToggle
    -0.40
     réparer
    -0.40
    ilirsiniz
    -0.39
     parcial
    -0.39
     elett
    -0.38
    gup
    -0.38
     bancaire
    -0.37
    渍
    -0.37
    POSITIVE LOGITS
     epidemio
    1.13
     epidemic
    1.12
     epidemiological
    1.08
     outbreak
    1.08
     epidemiology
    1.05
     Epide
    1.02
     epidemics
    1.02
     outbreaks
    1.00
     Epidemio
    0.98
    Epide
    0.98
    Activations Density 1.045%

    No Known Activations