© 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. 16-GEMMASCOPE-RES-16K
    11. 9263
    Prev
    Next
    INDEX
    Explanations

    the beginning of a new section or the introduction of a new topic

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

    Code, queries, and application initializations

    np_acts-logits-general · gemini-2.0-flash

    GUI component initialization/termination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.67
     élastique
    -0.63
    ogaster
    -0.62
    arrête
    -0.58
     betweenstory
    -0.57
    openqa
    -0.54
    cosse
    -0.53
    خواندن
    -0.52
    rrggbb
    -0.52
     banho
    -0.51
    POSITIVE LOGITS
    EndInit
    1.73
    ResumeLayout
    1.64
    ISupport
    1.56
    PerformLayout
    1.42
    BeginInit
    0.98
     تضيفلها
    0.75
    SuspendLayout
    0.70
     contextLoads
    0.67
     initComponents
    0.66
    GraphicsUnit
    0.65
    Activations Density 0.004%

    No Known Activations