© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11506
    Prev
    Next
    INDEX
    Explanations

    the word "Then" and its variations, indicating a focus on sequential events or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.49
    gains
    -0.46
    __::
    -0.43
    Inflater
    -0.42
    garis
    -0.40
    school
    -0.40
     weevil
    -0.40
    LayoutParams
    -0.40
    Hazard
    -0.39
     screenWidth
    -0.39
    POSITIVE LOGITS
     Then
    0.65
     Потом
    0.63
    Then
    0.62
     Anschließend
    0.60
     THEN
    0.59
     Затем
    0.59
     Daarna
    0.59
     subsequently
    0.56
    then
    0.56
    Затем
    0.56
    Activations Density 0.126%

    No Known Activations