© 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. 4441
    Prev
    Next
    INDEX
    Explanations

    terms related to eye conditions and symptoms of irritation

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

    Sensations or problems

    np_acts-logits-general · gemini-2.0-flash

    caused by physical sensations

    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
    /*
    -0.67
    enumi
    -0.61
    ophysical
    -0.59
    featureID
    -0.59
    Unlimited
    -0.57
     unlimited
    -0.57
    Brainz
    -0.56
    uminous
    -0.55
    moiselle
    -0.54
    kaj
    -0.53
    POSITIVE LOGITS
     due
    0.85
    due
    0.83
     devido
    0.79
     DUE
    0.68
     dû
    0.67
     Caused
    0.66
     caused
    0.65
     debido
    0.65
    Due
    0.64
    DUE
    0.64
    Activations Density 0.515%

    No Known Activations