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. 7201
    Prev
    Next
    INDEX
    Explanations

    terms related to mental health

    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
     referrerpolicy
    -0.63
    magin
    -0.57
    wußt
    -0.56
    Tikang
    -0.56
    __':
    
    -0.56
    UserScript
    -0.56
    друг
    -0.55
     }^{*}
    -0.54
    (;;)
    -0.54
    AsUp
    -0.54
    POSITIVE LOGITS
     health
    0.94
    health
    0.81
     Health
    0.77
     HEALTH
    0.69
    Health
    0.68
    ंदीखरीदारी
    0.64
     Mental
    0.62
     mental
    0.62
     illness
    0.61
     Heath
    0.60
    Activations Density 0.049%

    No Known Activations