© 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. 1-GEMMASCOPE-RES-16K
    6. 1841
    Prev
    Next
    INDEX
    Explanations

    references to leather and related materials, as well as specific angles in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.59
     مشين
    -0.50
    ngdoc
    -0.49
     Dutt
    -0.43
    Ссылки
    -0.42
    expandindo
    -0.41
    Сюжет
    -0.40
    пратки
    -0.40
    Manbalar
    -0.39
     ControllerBase
    -0.39
    POSITIVE LOGITS
     accident
    0.69
    MLLoader
    0.66
     injury
    0.61
    accident
    0.61
    injury
    0.59
     burn
    0.58
    trauma
    0.58
     Beef
    0.57
     trauma
    0.56
     goats
    0.56
    Activations Density 0.215%

    No Known Activations