Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114555
    Prev
    Next
    INDEX
    Explanations

    the presence of specific legal or investigative terms related to crime and public safety

    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
     generally
    -0.33
     Hu
    -0.32
     Wiel
    -0.32
     Widely
    -0.31
     aspect
    -0.30
     Freuden
    -0.30
     aspects
    -0.30
    有
    -0.30
    이터
    -0.29
     its
    -0.29
    POSITIVE LOGITS
    PerformLayout
    0.83
    ########.
    0.82
    IsMutable
    0.81
    
    0.75
    RegressionTest
    0.75
    Viited
    0.75
     nahilalakip
    0.75
    featureID
    0.69
    DeleteBehavior
    0.69
     للمعارف
    0.68
    Activations Density 0.023%

    No Known Activations