© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 8494
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs related to graphical system drawing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]}
    -0.37
    }))
    
    -0.34
    ()]);
    -0.34
     Mus
    -0.33
     ourselves
    -0.33
    ])):
    -0.32
     astore
    -0.32
     Li
    -0.32
    produkte
    -0.32
     ap
    -0.32
    POSITIVE LOGITS
     propOrder
    0.63
    EndContext
    0.62
    الحياه
    0.59
     defaultstate
    0.56
     Langkah
    0.52
     oprot
    0.52
    arangay
    0.52
    ьаж
    0.52
     Kebijakan
    0.52
     Budaya
    0.51
    Activations Density 0.013%

    No Known Activations