© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 8974
    Prev
    Next
    INDEX
    Explanations

    GUI component definitions and properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsdelivr
    -0.67
     Vikipedi
    -0.65
     виправивши
    -0.64
     Betracht
    -0.53
    getRuntime
    -0.52
     незавершена
    -0.51
     فريبيس
    -0.51
    dataTable
    -0.50
    numericUpDown
    -0.50
    gih
    -0.50
    POSITIVE LOGITS
     QLabel
    1.32
    QLabel
    1.24
    LabelTagHelper
    1.23
     JLabel
    1.14
    JLabel
    1.00
    MessageTagHelper
    0.99
     UILabel
    0.91
    InputLabel
    0.90
    jLabel
    0.90
    labelControl
    0.88
    Activations Density 0.011%

    No Known Activations