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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3405
    Prev
    Next
    INDEX
    Explanations

    geographical and administrative terms related to regions and divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     identidad
    -0.36
     Hauteur
    -0.31
     fuente
    -0.31
     pattes
    -0.31
     oficio
    -0.31
     orden
    -0.31
     transparence
    -0.29
     confiance
    -0.29
     Indah
    -0.29
     RELATIVE
    -0.29
    POSITIVE LOGITS
     regions
    0.77
     districts
    0.71
     NSCoder
    0.69
     Regions
    0.69
    regions
    0.64
     counties
    0.64
     cities
    0.63
     propOrder
    0.61
     coastal
    0.60
     localities
    0.60
    Activations Density 0.511%

    No Known Activations