© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13222
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cry" and other related terms that convey emotional distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     señores
    -0.38
     autorisé
    -0.34
     trebui
    -0.33
    Whoever
    -0.33
    TagMode
    -0.32
     prénom
    -0.32
     vescovo
    -0.31
    ffffff
    -0.31
     whoever
    -0.31
    值
    -0.31
    POSITIVE LOGITS
     cry
    2.23
     crypto
    2.00
     Cry
    1.99
     Crypto
    1.91
    Cry
    1.88
    cry
    1.85
    Crypto
    1.83
    crypto
    1.80
     CRY
    1.66
     cripto
    1.49
    Activations Density 0.128%

    No Known Activations