© 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. 20-GEMMASCOPE-RES-16K
    6. 123
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical user interface (GUI) components and code structure

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

    GTK Tree View or UI elements

    np_acts-logits-general · gemini-2.0-flash

    UI elements and structured text display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onActivityResult
    -0.78
    JNIEnv
    -0.65
    CloseOperation
    -0.62
    BindingSource
    -0.62
    WriteBarrier
    -0.59
    XmlAccessType
    -0.58
     rootReducer
    -0.57
    glMatrixMode
    -0.57
    insics
    -0.57
    jMenu
    -0.56
    POSITIVE LOGITS
    RenderAtEndOf
    0.87
     saites
    0.64
    Personensuche
    0.62
    tagHelperRunner
    0.61
    ंदीखरीदारी
    0.59
     texto
    0.57
    WebControls
    0.56
    Indented
    0.55
    IndentedString
    0.55
     חיצוניים
    0.54
    Activations Density 0.213%

    No Known Activations