© 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. 34-GEMMASCOPE-RES-16K
    11. 11556
    Prev
    Next
    INDEX
    Explanations

    dialogue exchanges that convey emotions and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grinning
    -0.68
     screaming
    -0.68
     smiling
    -0.68
     laughing
    -0.65
     yelling
    -0.64
     giggling
    -0.63
     smir
    -0.62
    tonode
    -0.61
     shouting
    -0.60
    laughing
    -0.57
    POSITIVE LOGITS
    Word
    0.39
    contentLoaded
    0.38
     Signalez
    0.36
     soft
    0.35
     Soft
    0.35
     feral
    0.34
     Word
    0.34
    RectangleBorder
    0.33
    Soft
    0.32
     Warm
    0.32
    Activations Density 0.090%

    No Known Activations