© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 3006
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "so" used in various emotional or conditional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.70
     Cæsar
    -0.70
     abomination
    -0.68
     Theſe
    -0.66
     myſelf
    -0.64
     DAG
    -0.64
     Monfieur
    -0.62
     Shakspeare
    -0.62
     Trunk
    -0.62
    ſelf
    -0.62
    POSITIVE LOGITS
     so
    1.03
     So
    0.93
    DockStyle
    0.88
     we
    0.80
    So
    0.79
     SO
    0.77
     therefore
    0.74
     therefor
    0.74
    もあるので
    0.72
    MigrationBuilder
    0.71
    Activations Density 0.317%

    No Known Activations