© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5589
    Prev
    Next
    INDEX
    Explanations

    references to personal challenges and emotional struggles

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

    mental health conditions, psychological states, and personal struggles, with a focus on emotional or behavioral challenges.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Autoritní
    -0.60
     للمعارف
    -0.57
    AddTagHelper
    -0.56
    LElement
    -0.49
     للاسماء
    -0.49
    compli
    -0.46
     Unexpected
    -0.45
    icordia
    -0.45
    webElementXpaths
    -0.44
    phosa
    -0.44
    POSITIVE LOGITS
     depressive
    0.50
     loneliness
    0.50
     isolation
    0.47
    istoitu
    0.40
     lonely
    0.39
     suicidal
    0.39
     Isolation
    0.38
     sad
    0.38
     melancholy
    0.37
     nihil
    0.37
    Activations Density 0.129%

    No Known Activations