© 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-2-9B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 6957
    Prev
    Next
    INDEX
    Explanations

    components and elements of user interface components in programming, specifically related to Java Swing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    numerusform
    -0.47
     kasarigan
    -0.47
    RTLR
    -0.44
    parseFrom
    -0.38
     Futuro
    -0.35
     bygget
    -0.34
    dung
    -0.34
     pê
    -0.33
    تقاوى
    -0.32
    OGND
    -0.32
    POSITIVE LOGITS
    jLabel
    1.45
    JLabel
    1.42
     JLabel
    1.41
     QLabel
    1.41
     jLabel
    1.34
    QLabel
    1.32
    LabelTagHelper
    1.12
    labelControl
    1.05
    PerformLayout
    0.98
     lbl
    0.93
    Activations Density 0.032%

    No Known Activations