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. 37-GEMMASCOPE-RES-16K
    6. 4551
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data processing and measurement operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.54
     astore
    -0.51
    PYX
    -0.50
     ویکی‌پدی
    -0.49
    AndEndTag
    -0.48
    webElementXpaths
    -0.43
    CONCLUSIONES
    -0.43
    ंदीखरीदारी
    -0.42
     PyLong
    -0.42
    bootstrapcdn
    -0.41
    POSITIVE LOGITS
     methods
    0.73
     method
    0.64
     procedure
    0.60
    方式
    0.59
     options
    0.58
     modes
    0.57
     process
    0.56
     styles
    0.56
     conditions
    0.56
     cycle
    0.55
    Activations Density 1.897%

    No Known Activations