© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 13612
    Prev
    Next
    INDEX
    Explanations

    medical terminology and conditions related to joint diseases, particularly arthritis

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

    joints, joint conditions, or arthritis

    np_acts-logits-general · gemini-2.0-flash

    joint conditions and surrounding anatomy

    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
    StackNavigator
    -0.70
    ViewFeatures
    -0.66
     Grosso
    -0.62
     considérons
    -0.61
    Autoritní
    -0.61
     Barclay
    -0.59
    ocyto
    -0.58
    mybatisplus
    -0.58
     RouterModule
    -0.56
    énario
    -0.55
    POSITIVE LOGITS
     joint
    1.34
     joints
    1.32
     Joints
    1.16
    Joint
    1.13
     Joint
    1.11
    joint
    1.11
    joints
    1.05
     arthritis
    1.04
     JOINT
    1.03
     Arthritis
    1.00
    Activations Density 0.478%

    No Known Activations