© 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. 31-GEMMASCOPE-RES-16K
    11. 6298
    Prev
    Next
    INDEX
    Explanations

    words related to speaking or communication

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

    words that start with "spo" (like "spooked," "spokesman," "spokesperson," "sponge," "spoofing," "spook").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.70
     مشين
    -0.67
     BoxFit
    -0.66
    лтамалар
    -0.66
     ujednoznacz
    -0.65
    IndentedString
    -0.63
    DotNetBar
    -0.63
    оргаш
    -0.61
    Сылтамалар
    -0.61
     estekak
    -0.59
    POSITIVE LOGITS
     Spo
    1.03
    spo
    0.99
    Spo
    0.98
     spo
    0.96
     SPO
    0.91
     spoil
    0.73
     spoiling
    0.73
     spoiled
    0.72
    SPO
    0.69
     spore
    0.69
    Activations Density 0.089%

    No Known Activations