© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 10834
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to object creation and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.92
    Personendaten
    -0.91
    
    -0.90
    
    -0.88
    𒊹
    -0.87
    Fordítás
    -0.86
    콯
    -0.86
    Ꮘ
    -0.85
    <unused43>
    -0.85
    
    -0.85
    POSITIVE LOGITS
     sisält
    0.14
     sekaligus
    0.13
     jäsen
    0.12
    ();*/
    0.12
     doigt
    0.11
     sientes
    0.11
     faptul
    0.11
     entsteht
    0.10
    );*/
    0.10
    ));
    0.10
    Activations Density 0.217%

    No Known Activations