© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14989
    Prev
    Next
    INDEX
    Explanations

    programming code snippets and structures related to URLs and data requests

    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
    Numerade
    -0.47
     Roads
    -0.44
    delaide
    -0.43
    ArgsConstructor
    -0.43
    TagMode
    -0.42
    specie
    -0.40
    Rhestr
    -0.40
    Roads
    -0.40
    rehensive
    -0.40
    GHIJKLM
    -0.40
    POSITIVE LOGITS
     url
    2.22
    url
    2.02
    Url
    1.46
     URL
    1.38
     Url
    1.30
    URL
    1.13
    setUrl
    1.09
    getUrl
    0.94
     urls
    0.94
    ByUrl
    0.81
    Activations Density 0.224%

    No Known Activations