© 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. 9939
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with mood disorders, particularly depression and its symptoms

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

    Contexts of depression and depressed mood

    np_acts-logits-general · gemini-2.0-flash

    depressive mood states

    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
    Formatted
    -0.47
    kost
    -0.43
    fas
    -0.42
     רא
    -0.42
    vener
    -0.41
     kinematic
    -0.41
    tiglia
    -0.40
    <tbody>
    -0.40
    Ги
    -0.40
     auto
    -0.40
    POSITIVE LOGITS
     happiness
    1.48
     happier
    1.43
     Happiness
    1.41
     mood
    1.36
    happiness
    1.36
    Happiness
    1.32
     cheerful
    1.27
     moods
    1.21
     happy
    1.21
     happiest
    1.20
    Activations Density 0.233%

    No Known Activations