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. 25-GEMMASCOPE-RES-16K
    6. 8864
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ability or action related to teaching, learning, and sewing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
     Singing
    -0.94
     Painting
    -0.84
    painting
    -0.81
     baking
    -0.80
    publishing
    -0.79
    Singing
    -0.79
     Breeding
    -0.79
     singing
    -0.78
     printing
    -0.77
     painting
    -0.77
    POSITIVE LOGITS
    SystemColors
    0.59
    Being
    0.50
    EnableWeb
    0.50
    Previously
    0.49
    Consequently
    0.48
    Mainly
    0.48
    vantaged
    0.47
    TagHelper
    0.47
    eably
    0.46
     getItemCount
    0.46
    Activations Density 0.784%

    No Known Activations