© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4521
    Prev
    Next
    INDEX
    Explanations

    phrases related to fishing equipment and its usage

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

    fishing

    np_acts-logits-general · gemini-2.0-flash

    fishing, bait, tackle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.73
     محفوظة
    -0.67
     تضيفلها
    -0.67
    Diwedd
    -0.64
    DoubleQuotes
    -0.60
    ToBounds
    -0.59
     мәкал
    -0.57
     MainAxisSize
    -0.57
     Wicidata
    -0.56
    URIComponent
    -0.55
    POSITIVE LOGITS
     fishing
    1.09
     fished
    1.03
     Fishing
    0.95
    fishing
    0.94
     anglers
    0.94
    Fishing
    0.93
     angler
    0.93
     fisherman
    0.90
    fish
    0.87
     fish
    0.86
    Activations Density 0.075%

    No Known Activations