© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97633
    Prev
    Next
    INDEX
    Explanations

    references to Common Weakness Enumeration (CWE) codes associated with software vulnerabilities

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

    CWE identifiers

    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
     étrangère
    -0.35
     dictadura
    -0.32
     étr
    -0.31
     estatu
    -0.31
     Zusatz
    -0.30
     Bischof
    -0.30
    bertas
    -0.30
     aguj
    -0.30
     seleccionar
    -0.30
     encontraron
    -0.30
    POSITIVE LOGITS
     CWE
    6.09
    CWE
    3.36
     betweenstory
    0.94
     CW
    0.92
    oa̍t
    0.91
     OMITBAD
    0.89
     незавершена
    0.80
    :✨
    0.78
     CVC
    0.77
    Rüyada
    0.77
    Activations Density 0.000%

    No Known Activations