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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10992
    Prev
    Next
    INDEX
    Explanations

    conditions related to medical complications and treatments

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

    Followed by "." and a capitalized word

    np_acts-logits-general · gemini-2.0-flash

    medical cases or patients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.53
     piacere
    -0.52
     hippocampus
    -0.50
    
    -0.49
    存于互联网档案馆
    -0.49
    hnia
    -0.48
     kne
    -0.47
    šķ
    -0.47
     potete
    -0.47
    DetailActivity
    -0.46
    POSITIVE LOGITS
     patients
    0.99
     Patients
    0.98
     patient
    0.97
    Patients
    0.91
    patients
    0.90
     clinically
    0.88
    patient
    0.84
     pacientes
    0.83
     paciente
    0.82
     Patient
    0.81
    Activations Density 6.236%

    No Known Activations