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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4311
    Prev
    Next
    INDEX
    Explanations

    words related to temporal events or sequences

    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
     then
    -1.06
     alors
    -0.96
     entonces
    -0.93
     now
    -0.85
     allora
    -0.81
     damaligen
    -0.81
    alors
    -0.79
    then
    -0.78
     Then
    -0.76
     então
    -0.75
    POSITIVE LOGITS
     proceeded
    0.99
     proceed
    0.94
     comes
    0.84
     proceeds
    0.82
     again
    0.80
     followed
    0.79
    proceed
    0.79
     proceeding
    0.75
     cometh
    0.72
    followed
    0.72
    Activations Density 0.265%

    No Known Activations