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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7143
    Prev
    Next
    INDEX
    Explanations

    terms related to keyboards and keyboard functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الدراسه
    -0.76
     Spit
    -0.67
    lapsingToolbar
    -0.64
    Vidite
    -0.64
    éfono
    -0.64
    ResumeLayout
    -0.63
     ComVisible
    -0.62
     autorisés
    -0.62
    AnimationsModule
    -0.60
    tagHelper
    -0.60
    POSITIVE LOGITS
     Keyboard
    1.23
     keyboard
    1.23
     PropTypes
    1.11
    keyboard
    1.10
    Keyboard
    1.05
     keyboards
    0.94
    ArgsConstructor
    0.85
    键盘
    0.85
    キーボード
    0.80
     clavier
    0.77
    Activations Density 0.012%

    No Known Activations