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

    Neuronpedia

    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. 11-GEMMASCOPE-RES-16K
    11. 8199
    Prev
    Next
    INDEX
    Explanations

    cryptographic terms and patterns related to data encryption and hashing mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.65
    AnimationsModule
    -0.65
    CppMethod
    -0.64
    haikusbot
    -0.64
     informée
    -0.63
    Билгалдахарш
    -0.60
    تقاوى
    -0.57
    PerformLayout
    -0.57
    новниш
    -0.56
    elemField
    -0.56
    POSITIVE LOGITS
     рода
    0.38
     dedans
    0.35
     later
    0.31
    altezza
    0.31
     affaires
    0.31
    @@@@@
    0.30
    Setter
    0.30
    깥
    0.30
     žem
    0.30
     phân
    0.29
    Activations Density 3.751%

    No Known Activations