© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 146
    Prev
    Next
    INDEX
    Explanations

    references to time, specifically indicating late occurrences

    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
     CreateTagHelper
    -0.71
    UnusedPrivate
    -0.61
    SequentialGroup
    -0.58
     segera
    -0.55
    ktı
    -0.54
     لينك
    -0.54
     katanya
    -0.51
     recién
    -0.51
     bientôt
    -0.51
    "?>
    -0.50
    POSITIVE LOGITS
    comers
    0.92
    comer
    0.85
     afternoon
    0.78
     lamented
    0.70
     night
    0.65
     arrivals
    0.62
     afternoons
    0.61
     risers
    0.60
     bloom
    0.59
     stage
    0.58
    Activations Density 0.174%

    No Known Activations