© 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. 34-GEMMASCOPE-RES-16K
    11. 10852
    Prev
    Next
    INDEX
    Explanations

    words that contain the substring "sp"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endpush
    -0.43
    HostException
    -0.37
     om
    -0.34
     Meg
    -0.34
     transfieras
    -0.33
     continu
    -0.32
    PMailer
    -0.32
    enderror
    -0.32
    ciuta
    -0.31
    ContentValues
    -0.31
    POSITIVE LOGITS
     sp
    0.96
     Sp
    0.90
    Sp
    0.81
    sp
    0.77
     spiked
    0.65
     Spal
    0.63
     SP
    0.61
     ſp
    0.59
    GEBURTSDATUM
    0.58
     spi
    0.56
    Activations Density 0.175%

    No Known Activations