© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10459
    Prev
    Next
    INDEX
    Explanations

    phrases and actions related to merging data or content

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

    Mentions the word "merge"

    np_acts-logits-general · gemini-2.0-flash

    merging different items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PrintWriter
    -0.46
    ptonshire
    -0.45
    BeginInit
    -0.43
     PopupWindow
    -0.43
    ExecuteReader
    -0.41
    __':
    -0.41
     ActiveRecord
    -0.40
    最快更新
    -0.40
    IGraphics
    -0.39
    __":
    -0.38
    POSITIVE LOGITS
     merge
    1.98
     merging
    1.81
     Merge
    1.81
     merger
    1.73
     merges
    1.70
     merged
    1.70
    Merge
    1.70
    merge
    1.62
     Merger
    1.52
     mergers
    1.43
    Activations Density 0.516%

    No Known Activations