Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15682
    Prev
    Next
    INDEX
    Explanations

    expressions of sadness and mourning

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

    Sadness and melancholy

    np_acts-logits-general · gemini-2.0-flash

    bemoaned or mourning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     Issus
    -0.51
     simplifié
    -0.51
     isInitialized
    -0.49
    atars
    -0.49
    Зноскі
    -0.48
     protoimpl
    -0.48
    łys
    -0.47
     lcm
    -0.47
    Mille
    -0.47
     ffilmiau
    -0.46
    POSITIVE LOGITS
     melancholy
    1.56
     sad
    1.54
     sadness
    1.52
     melancho
    1.43
     mourning
    1.40
     mournful
    1.40
    Sad
    1.38
     saddest
    1.37
     sorrowful
    1.36
     depressing
    1.36
    Activations Density 0.219%

    No Known Activations