Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5123
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data collection and analysis methods in environmental studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyCulture
    -0.50
    ืด
    -0.39
    ransition
    -0.39
     мәкал
    -0.37
    TabStop
    -0.36
    JIS
    -0.36
    uxxxx
    -0.35
     KOL
    -0.35
     grave
    -0.35
    막
    -0.35
    POSITIVE LOGITS
     satellite
    1.14
     satellites
    1.08
     Satellite
    1.01
    satellite
    0.98
     satélite
    0.94
    Satellite
    0.93
     Landsat
    0.92
     Satellites
    0.92
    Sat
    0.91
     satel
    0.89
    Activations Density 0.291%

    No Known Activations