© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1501
    Prev
    Next
    INDEX
    Explanations

    references to suicidal ideation and chronic mental health conditions

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

    terms related to the relationship between chronic pain and mental health, particularly depression and suicidal thoughts

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

    suicidal thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.89
    TintMode
    -0.77
     uintptr
    -0.74
    GEBURTSDATUM
    -0.74
     actionMode
    -0.71
     defaultstate
    -0.69
    IonicModule
    -0.69
    Pratique
    -0.68
    DockStyle
    -0.67
     Spro
    -0.67
    POSITIVE LOGITS
     thoughts
    1.31
     Thoughts
    1.06
    thoughts
    1.01
    Thoughts
    0.99
     thought
    0.93
     THOUGHTS
    0.88
     pensamientos
    0.87
     pensées
    0.85
     pensieri
    0.84
     Gedanken
    0.80
    Activations Density 0.221%

    No Known Activations