© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 99
    Prev
    Next
    INDEX
    Explanations

    words related to attention or focus

    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
     يتيمه
    -0.67
    хьтан
    -0.63
    bootstrapcdn
    -0.59
     autorytatywna
    -0.57
    WebVitals
    -0.54
    IsMutable
    -0.53
     חיצוניים
    -0.53
    Autoritní
    -0.52
    yntaxException
    -0.51
     NSCoder
    -0.50
    POSITIVE LOGITS
     attention
    2.48
    attention
    1.98
     Attention
    1.79
    Attention
    1.67
     ATTENTION
    1.58
     attentions
    1.48
     atención
    1.46
    attenzione
    1.45
     atenção
    1.44
     aandacht
    1.44
    Activations Density 0.416%

    No Known Activations