© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3353
    Prev
    Next
    INDEX
    Explanations

    repetitions of the phrase "so" used for emphasis

    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
     Chwiliwch
    -0.57
     defaultstate
    -0.52
    AnimationsModule
    -0.51
     AppCompatTheme
    -0.48
    /**
    -0.47
    ruptedException
    -0.47
    <?
    -0.47
    rshire
    -0.46
     hemel
    -0.46
    ستاگرام
    -0.45
    POSITIVE LOGITS
     so
    3.22
    so
    2.16
    So
    1.85
     så
    1.83
     So
    1.77
     так
    1.75
     SO
    1.55
     begitu
    1.53
     così
    1.51
     ſo
    1.49
    Activations Density 0.169%

    No Known Activations