© 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. 31-GEMMASCOPE-RES-16K
    11. 6742
    Prev
    Next
    INDEX
    Explanations

    terms related to input methods and keyboard functionality

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

    words and phrases related to keyboards and keyboard input methods.

    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
     quenching
    -0.44
     drzwi
    -0.41
    ServletException
    -0.39
     hunger
    -0.38
     quench
    -0.38
     invokingState
    -0.38
    sweetalert
    -0.37
     silnika
    -0.37
     Parr
    -0.37
     starve
    -0.36
    POSITIVE LOGITS
     keyboard
    1.51
     Keyboard
    1.30
    keyboard
    1.23
     keyboards
    1.22
    Keyboard
    1.16
     teclado
    1.05
     typing
    1.03
     клавиа
    1.03
    キーボード
    1.03
    键盘
    1.02
    Activations Density 0.247%

    No Known Activations