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. 16-GEMMASCOPE-RES-16K
    6. 1400
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotional pain and loss

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

    sadness or grief

    np_acts-logits-general · gemini-2.0-flash

    emotional distress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Haha
    -0.47
    Hehe
    -0.45
     beneficial
    -0.45
    ⌐
    -0.45
    ään
    -0.45
     đương
    -0.44
    (")");
    -0.44
    haha
    -0.44
     ứng
    -0.44
     minor
    -0.43
    POSITIVE LOGITS
     grieving
    0.97
     grief
    0.95
     heartbreaking
    0.95
     tragedy
    0.92
     heartbreak
    0.90
     tragically
    0.89
     heartbroken
    0.89
     devastated
    0.84
     traged
    0.84
     Grief
    0.83
    Activations Density 0.194%

    No Known Activations