© 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. 9064
    Prev
    Next
    INDEX
    Explanations

    scientific names of catfish species

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

    Fish species names and fish as food

    np_acts-logits-general · gemini-2.0-flash

    fish names and scientific suffixes

    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
     EconPapers
    -0.81
    Geplaatst
    -0.76
     المعيارى
    -0.75
     defaultstate
    -0.69
    ThroughAttribute
    -0.68
    TemporalType
    -0.67
     незавершена
    -0.66
     NSCoder
    -0.64
    __(/*!
    -0.63
     виправивши
    -0.63
    POSITIVE LOGITS
     fish
    1.30
     Fish
    1.11
    fish
    1.07
    Fish
    1.05
     fishes
    0.91
     ikan
    0.87
     fisheries
    0.81
     fishing
    0.79
     fishery
    0.76
     poissons
    0.76
    Activations Density 0.182%

    No Known Activations