© 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. 10760
    Prev
    Next
    INDEX
    Explanations

    expressions of love and affection between individuals

    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
     gyhoeddwyd
    -0.37
     Effectively
    -0.36
     Lowest
    -0.35
    まさかの
    -0.34
     effectively
    -0.34
    Werdegang
    -0.34
    contentPane
    -0.33
    CRS
    -0.33
    ligente
    -0.33
    editForm
    -0.33
    POSITIVE LOGITS
     dearly
    1.08
     immensely
    0.89
     mucho
    0.79
     enemmän
    0.77
     much
    0.75
     больше
    0.73
     autant
    0.72
     more
    0.72
     unconditionally
    0.68
     більше
    0.67
    Activations Density 0.210%

    No Known Activations