© 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. 22-GEMMASCOPE-RES-16K
    11. 11391
    Prev
    Next
    INDEX
    Explanations

    mentions of attention in various contexts, particularly its effects and importance

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

    "attention"

    np_acts-logits-general · gemini-2.0-flash

    paid attention to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.57
    DotNetBar
    -0.52
    Segoe
    -0.51
     torus
    -0.49
    ArgsConstructor
    -0.49
    etCode
    -0.49
    anium
    -0.48
    ViewImports
    -0.48
     والخ
    -0.48
    sy
    -0.48
    POSITIVE LOGITS
     Attention
    1.08
     attention
    1.02
    Attention
    0.95
    attention
    0.87
     ATTENTION
    0.85
     span
    0.83
    ATTENTION
    0.81
    Personensuche
    0.80
     paid
    0.80
     spans
    0.79
    Activations Density 0.069%

    No Known Activations