Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8004
    Prev
    Next
    INDEX
    Explanations

    occurrences of UI-related code segments in an Android application framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WireFormatLite
    -1.16
    CloseOperation
    -1.03
    Geplaatst
    -1.01
     surla
    -0.94
    DebuggerNonUser
    -0.90
    URLException
    -0.89
     ExecuteAsync
    -0.87
    %");
    -0.85
    LayoutStyle
    -0.84
    MemoryWarning
    -0.82
    POSITIVE LOGITS
    VersionUID
    0.69
    ViewImports
    0.68
    intellij
    0.57
    ContentAsync
    0.57
    LabelTagHelper
    0.56
    dropna
    0.55
    ```
    0.55
    斯坦
    0.53
    vac
    0.51
     Miser
    0.51
    Activations Density 0.007%

    No Known Activations