© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 6242
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to depression and its symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.51
     nahilalakip
    -0.50
    verifyException
    -0.49
    CreateMap
    -0.47
     Scramble
    -0.46
     scrambling
    -0.45
    Tikang
    -0.44
     scramble
    -0.43
    ReusableCell
    -0.42
     informée
    -0.42
    POSITIVE LOGITS
     depression
    2.00
     depressed
    1.89
     depressive
    1.77
    depression
    1.68
     Depression
    1.65
    Depression
    1.60
     depres
    1.60
     depresión
    1.58
     depressing
    1.55
     депре
    1.52
    Activations Density 0.461%

    No Known Activations