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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10736
    Prev
    Next
    INDEX
    Explanations

    terms related to personal struggles and trauma, especially in the context of gender and mental health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.59
    RenderAtEndOf
    -0.46
    Халык
    -0.41
    CELLANEOUS
    -0.40
    นั้น
    -0.39
    ifrance
    -0.39
     solches
    -0.36
     contextLoads
    -0.36
     NSError
    -0.36
    PerformLayout
    -0.35
    POSITIVE LOGITS
     who
    4.34
    who
    3.00
     whom
    2.94
     quien
    2.81
     whose
    2.47
     którzy
    2.36
     quién
    2.36
    Who
    2.34
     quienes
    2.34
     Who
    2.30
    Activations Density 3.071%

    No Known Activations