© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13562
    Prev
    Next
    INDEX
    Explanations

    the word "of" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.62
     AppCompatTheme
    -0.51
    Sklici
    -0.51
    MigrationBuilder
    -0.51
     nahilalakip
    -0.47
    PhysRevD
    -0.45
     razas
    -0.44
    postIndex
    -0.44
     linkovi
    -0.43
     informée
    -0.43
    POSITIVE LOGITS
     kinda
    0.82
     Kinda
    0.74
     sorta
    0.73
    kinda
    0.68
    Kinda
    0.64
     kind
    0.63
     Almost
    0.62
     pretty
    0.61
     almost
    0.61
    Almost
    0.56
    Activations Density 0.101%

    No Known Activations