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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 9044
    Prev
    Next
    INDEX
    Explanations

    references to materials, particularly those associated with color and aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doInBackground
    -0.96
     HasFactory
    -0.55
    Yogurt
    -0.55
     Scarecrow
    -0.54
    adaptiveStyles
    -0.54
    ImageContext
    -0.53
    Filmografie
    -0.52
     lignin
    -0.50
     pinulongan
    -0.50
    SpringBootTest
    -0.49
    POSITIVE LOGITS
     gem
    1.32
     gemstone
    1.30
     gemstones
    1.28
     gems
    1.26
     crystal
    1.22
     crystals
    1.17
     Gem
    1.17
    Gem
    1.14
     stones
    1.14
    gems
    1.10
    Activations Density 0.216%

    No Known Activations