© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3778
    Prev
    Next
    INDEX
    Explanations

    topics related to emotional and psychological suffering and trauma

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

    Negative emotions and suffering

    np_acts-logits-general · gemini-2.0-flash

    pain and suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.64
     referenties
    -0.57
    Hochspringen
    -0.55
    ')['
    -0.54
     Effectiveness
    -0.54
    ագրություններ
    -0.52
     Verhältnis
    -0.52
    HomeAsUpEnabled
    -0.51
    YMMV
    -0.51
     reimbur
    -0.51
    POSITIVE LOGITS
     misery
    0.90
     uncertainty
    0.90
     illness
    0.89
     injury
    0.88
     violence
    0.88
     disorder
    0.88
     unhappiness
    0.86
     pain
    0.86
     confusion
    0.86
     disease
    0.85
    Activations Density 1.030%

    No Known Activations