Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 7140
    Prev
    Next
    INDEX
    Explanations

    adjectives associated with beauty and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.54
     beautiful
    -0.50
    MemoryWarning
    -0.46
    beautiful
    -0.46
    bootstrapcdn
    -0.45
    openConnection
    -0.45
     wundersch
    -0.45
     favorite
    -0.44
    Beautiful
    -0.43
     Beautiful
    -0.43
    POSITIVE LOGITS
     little
    0.64
     scenery
    0.59
     sunsets
    0.59
     smelling
    0.56
     looking
    0.55
     things
    0.54
     sounding
    0.54
     thing
    0.53
     colors
    0.50
     colours
    0.49
    Activations Density 0.237%

    No Known Activations