© 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. 2-GEMMASCOPE-RES-16K
    11. 11066
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with simplicity and ease of use in programming or technology contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeera
    -0.49
    wendigkeit
    -0.43
     cheminée
    -0.42
    ьаж
    -0.42
     Happened
    -0.41
     iNdEx
    -0.40
     Coverage
    -0.39
     Blessing
    -0.39
    хьтан
    -0.39
     Matter
    -0.39
    POSITIVE LOGITS
     Private
    0.94
     Small
    0.94
     Simple
    0.94
     Advanced
    0.94
    Dynamic
    0.92
    Simple
    0.91
     Dynamic
    0.91
     Personal
    0.90
     Automatic
    0.89
     Permanent
    0.89
    Activations Density 0.562%

    No Known Activations