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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101548
    Prev
    Next
    INDEX
    Explanations

    references to Common Weakness Enumeration (CWE) identifiers related to software vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    zerland
    -0.38
    principalColumn
    -0.35
    setVerticalGroup
    -0.35
    gemaakt
    -0.33
    XmlAccessorType
    -0.33
     
    -0.33
     برانيه
    -0.32
     protoimpl
    -0.32
     unheard
    -0.32
     копия
    -0.32
    POSITIVE LOGITS
     CWE
    0.99
    MigrationBuilder
    0.75
    hyrchwyd
    0.67
     ſind
    0.65
    ValueStyle
    0.64
    rungsseite
    0.63
    ACHUSET
    0.63
     kasarigan
    0.61
    
    0.60
     otomatig
    0.59
    Activations Density 0.016%

    No Known Activations