© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 37975
    Prev
    Next
    INDEX
    Explanations

    references to watersheds and catchments in the context of environmental studies

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

    water catchment areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     super
    -0.39
    imab
    -0.35
    Ghost
    -0.33
    getitem
    -0.32
     sof
    -0.32
     Ghost
    -0.32
    noOf
    -0.32
     tun
    -0.32
    hide
    -0.31
     ghost
    -0.31
    POSITIVE LOGITS
     watershed
    1.04
     watersheds
    1.00
     Watershed
    0.96
     catchment
    0.74
     Infórmanos
    0.70
     upstream
    0.65
    Waters
    0.64
     ecosystems
    0.61
     ecosystem
    0.60
    transQ
    0.60
    Activations Density 0.005%

    No Known Activations