© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 125460
    Prev
    Next
    INDEX
    Explanations

    concepts related to harvesting and reaping benefits or rewards

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

    harvest and reap

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AndEndTag
    -0.59
     للاسماء
    -0.56
     mud
    -0.54
     MUD
    -0.52
    mud
    -0.52
    MUD
    -0.52
    mobileqq
    -0.51
    点此举报
    -0.49
     lapse
    -0.49
     Mud
    -0.49
    POSITIVE LOGITS
     harvest
    0.91
     cosecha
    0.83
    Harvest
    0.82
     harvesting
    0.78
     harvests
    0.77
     Harvesting
    0.76
     harvested
    0.76
    harvest
    0.73
     Harvest
    0.72
     récolte
    0.63
    Activations Density 0.015%

    No Known Activations