© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 6971
    Prev
    Next
    INDEX
    Explanations

    terms associated with programming vulnerabilities and biological signaling mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.42
     ocho
    -0.42
    MigrationBuilder
    -0.39
    第六
    -0.39
     acht
    -0.39
    çalves
    -0.38
     cinquième
    -0.38
     fifth
    -0.38
     sexto
    -0.38
     يتيمه
    -0.38
    POSITIVE LOGITS
     three
    1.70
     Three
    1.68
    3
    1.62
    Three
    1.55
    three
    1.52
     THREE
    1.45
     trois
    1.44
    THREE
    1.41
     drei
    1.36
     üç
    1.32
    Activations Density 5.364%

    No Known Activations