© 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. 20-GEMMASCOPE-RES-16K
    11. 2571
    Prev
    Next
    INDEX
    Explanations

    emotional expressions of sadness and vulnerability

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

    emotional or intense personal reactions (like crying, feeling overwhelmed, or being deeply moved).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    tagHelperRunner
    -0.54
    ngrx
    -0.47
     Ensino
    -0.45
    maining
    -0.44
    ſelves
    -0.44
    Véase
    -0.43
    Freund
    -0.43
    INTEN
    -0.42
    atchewan
    -0.42
    indor
    -0.42
    POSITIVE LOGITS
     tears
    0.60
     weeping
    0.54
     sobbing
    0.52
    tears
    0.48
     lágrimas
    0.48
     crying
    0.46
     larmes
    0.44
     weep
    0.44
     wept
    0.44
     sobs
    0.43
    Activations Density 0.095%

    No Known Activations