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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 5703
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures, particularly those associated with HTTP request handling and parsing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lud
    -0.46
    Lud
    -0.41
     LUD
    -0.39
    erevan
    -0.37
     Piel
    -0.36
     Grü
    -0.36
     farmer
    -0.35
     Farmers
    -0.34
     farmers
    -0.34
    issory
    -0.34
    POSITIVE LOGITS
     headers
    1.28
     Headers
    1.20
    headers
    1.13
    Headers
    1.08
     header
    1.05
     Header
    1.00
    Header
    0.95
    header
    0.94
     HttpHeaders
    0.88
     HEADER
    0.87
    Activations Density 1.274%

    No Known Activations