© 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. 28-GEMMASCOPE-RES-16K
    11. 3819
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diagnoses

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

    a diagnosis

    np_acts-logits-general · gemini-2.0-flash

    making a medical diagnosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    huana
    -0.48
     CURIAM
    -0.47
    mender
    -0.46
     Chwiliwch
    -0.45
     Reference
    -0.43
     rel
    -0.43
     oud
    -0.43
     interfer
    -0.43
     redi
    -0.43
    sail
    -0.42
    POSITIVE LOGITS
     diagnosis
    1.72
     diagnoses
    1.43
     diagnose
    1.39
     Diagnosis
    1.38
     diagnosed
    1.34
     Diagnose
    1.32
    diagnosis
    1.32
    Diagnosis
    1.23
     diagno
    1.20
     diagnosing
    1.16
    Activations Density 0.533%

    No Known Activations