© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5814
    Prev
    Next
    INDEX
    Explanations

    references to HTTP request methods, specifically "POST"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldNumber
    -0.75
    webElementXpaths
    -0.58
    XtraReports
    -0.57
    pulumi
    -0.56
    >--}}
    -0.53
    endregion
    -0.51
    bringt
    -0.49
     disconnect
    -0.49
    :✨
    -0.48
    ffichage
    -0.47
    POSITIVE LOGITS
    post
    1.46
    POST
    1.34
    HttpPost
    1.12
     post
    1.05
    AddTagHelper
    1.03
    PostMapping
    1.00
     POST
    0.98
     doPost
    0.86
    GraphicsUnit
    0.84
    ポスト
    0.81
    Activations Density 0.115%

    No Known Activations