© 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. 36-GEMMASCOPE-RES-16K
    11. 9010
    Prev
    Next
    INDEX
    Explanations

    the word "so" used in various contexts, particularly emphasizing its frequency and importance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.60
    pushFollow
    -0.59
    tagHelperRunner
    -0.57
     propOrder
    -0.52
    RefNanny
    -0.52
    RTLI
    -0.52
    hoeddwyd
    -0.51
    CDCl
    -0.49
    WriteAttribute
    -0.47
     actionMode
    -0.47
    POSITIVE LOGITS
     far
    3.55
    far
    2.69
    Far
    2.41
     Far
    2.31
     FAR
    2.17
    FAR
    1.92
     jauh
    1.88
    远
    1.85
     далеко
    1.83
    遠
    1.76
    Activations Density 0.443%

    No Known Activations