Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 543
    Prev
    Next
    INDEX
    Explanations

    terms related to the diagnosis and symptoms of depression, particularly those with somatic connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.90
     дописавши
    -0.73
     للمعارف
    -0.67
    urtstag
    -0.67
    исленность
    -0.64
    脚注の使い方
    -0.63
     بيها
    -0.63
     autorytatywna
    -0.63
    acabana
    -0.63
     getRule
    -0.62
    POSITIVE LOGITS
     mental
    1.53
     depression
    1.51
     Mental
    1.35
     suicide
    1.31
     psychiatric
    1.28
    Mental
    1.28
     Depression
    1.28
    Depression
    1.27
     depressive
    1.23
     suicidal
    1.23
    Activations Density 0.528%

    No Known Activations