© 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. 21-GEMMASCOPE-RES-16K
    6. 1797
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface (UI)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haft
    -0.66
     meantime
    -0.64
    ![
    -0.61
    middels
    -0.61
    下载附件
    -0.59
    IndentedString
    -0.58
    ///</
    -0.57
     frattempo
    -0.57
     NavController
    -0.57
    mogorov
    -0.56
    POSITIVE LOGITS
     ui
    0.69
    Bronnen
    0.63
     UI
    0.59
    tagext
    0.59
    面的
    0.58
     createState
    0.57
     widgets
    0.57
     Interfaces
    0.57
     interfaces
    0.56
    ̯
    0.56
    Activations Density 0.068%

    No Known Activations