© 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. 25-GEMMASCOPE-RES-16K
    11. 15591
    Prev
    Next
    INDEX
    Explanations

    expressions of affection and intimate connections among individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Camp
    -0.30
     potensi
    -0.29
     interests
    -0.28
     interessiert
    -0.28
     ugyan
    -0.28
    Camp
    -0.28
     campagna
    -0.28
     camp
    -0.28
    生
    -0.27
    swf
    -0.26
    POSITIVE LOGITS
     cuddle
    1.01
     cuddling
    0.98
     hug
    0.98
     hugging
    0.97
     hugged
    0.94
     hugs
    0.93
     cudd
    0.87
     cuddly
    0.81
    hugs
    0.80
    Hug
    0.79
    Activations Density 0.172%

    No Known Activations