© 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. 24-GEMMASCOPE-RES-16K
    11. 7877
    Prev
    Next
    INDEX
    Explanations

    keywords related to attention in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "attention"

    np_acts-logits-general · gemini-2.0-flash

    paying attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.62
    IsMutable
    -0.54
    DebuggerNonUser
    -0.50
    EndInit
    -0.50
    oa̍t
    -0.49
    bootstrapcdn
    -0.49
    GEBURTSDATUM
    -0.48
    ospel
    -0.46
    isateur
    -0.45
    بوابة
    -0.45
    POSITIVE LOGITS
     attention
    3.37
    attention
    2.69
     Attention
    2.61
    Attention
    2.42
     ATTENTION
    2.27
     attentions
    2.02
     atención
    1.98
     aandacht
    1.97
     atenção
    1.91
    attenzione
    1.89
    Activations Density 0.249%

    No Known Activations