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. 11-GEMMASCOPE-RES-16K
    6. 8523
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript elements related to button functionality within a web development context

    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
    GEBURTSDATUM
    -0.77
     Италијани
    -0.54
    mybatisplus
    -0.50
     فريبيس
    -0.49
    CompleteListener
    -0.45
     organisational
    -0.44
    endphp
    -0.44
    BufferException
    -0.43
    jsonwebtoken
    -0.42
    стероид
    -0.39
    POSITIVE LOGITS
    fxml
    0.57
    setupUi
    0.50
    transQ
    0.50
    دانشنامهٔ
    0.48
     hObject
    0.44
     jsPsych
    0.43
    ########.
    0.42
    ipes
    0.42
    AddHtmlAttribute
    0.41
    FXML
    0.41
    Activations Density 0.226%

    No Known Activations