Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8092
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.58
    abestanden
    -0.51
     fubject
    -0.51
    AddHtmlAttribute
    -0.50
    外部連結
    -0.50
     ComVisible
    -0.48
     ſta
    -0.48
     deſt
    -0.47
     anſ
    -0.46
    Искәрмәләр
    -0.46
    POSITIVE LOGITS
    🔕
    0.55
     korzyst
    0.45
    parsedMessage
    0.43
    ariConfig
    0.42
    MENAFN
    0.42
     يتيمه
    0.39
    addPreferredGap
    0.38
    ጋ
    0.38
    dotenv
    0.37
    inox
    0.37
    Activations Density 0.214%

    No Known Activations