© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58127
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to overflow scenarios in data handling or programming

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

    buffer overflow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Major
    -0.40
    Fir
    -0.38
    Agent
    -0.38
     vorbe
    -0.37
    SqlClient
    -0.36
    agent
    -0.36
     Jpn
    -0.35
    Michigan
    -0.35
    Jess
    -0.35
    a
    -0.35
    POSITIVE LOGITS
     Overflow
    1.32
     overflow
    1.32
    Overflow
    1.27
    overflow
    1.18
     overflows
    0.99
     overflowing
    0.89
     outflow
    0.77
    溢
    0.69
     Spill
    0.67
    ChildScrollView
    0.66
    Activations Density 0.003%

    No Known Activations