© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 95812
    Prev
    Next
    INDEX
    Explanations

    medical research contexts and terminology related to patient assessments and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hospital and clinic locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.51
    EDEFAULT
    -0.46
    InputTagHelper
    -0.46
    ----</
    -0.38
    Portale
    -0.38
     ISTAT
    -0.38
     payé
    -0.37
     doInBackground
    -0.36
    ptian
    -0.36
    ussis
    -0.35
    POSITIVE LOGITS
     clinic
    0.64
     clinics
    0.55
    clinic
    0.54
     Clinic
    0.53
     Clinics
    0.52
    лтемелер
    0.51
    enderror
    0.51
    requireNonNull
    0.48
    Referencie
    0.48
     thiệu
    0.47
    Activations Density 0.175%

    No Known Activations