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. 4-GEMMASCOPE-RES-16K
    6. 12268
    Prev
    Next
    INDEX
    Explanations

    instances of the word "recent"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.89
     considérons
    -0.73
    denly
    -0.70
    SourceChecksum
    -0.70
    таратура
    -0.69
     mukana
    -0.67
     afterwards
    -0.67
     permanently
    -0.67
    جغرافيا
    -0.66
     mères
    -0.64
    POSITIVE LOGITS
     recent
    2.24
    recent
    2.02
     RECENT
    1.94
    Recent
    1.86
     Recent
    1.84
    RECENT
    1.62
     recente
    1.52
     reciente
    1.36
     recenti
    1.35
     previous
    1.33
    Activations Density 0.127%

    No Known Activations