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-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39104
    Prev
    Next
    INDEX
    Explanations

    references to the NGINX web server and its configuration options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.84
    TagMode
    -0.65
    +:+
    -0.54
    MigrationBuilder
    -0.51
    iner
    -0.49
    findpost
    -0.48
    InjectAttribute
    -0.48
    RepeatedField
    -0.46
     Wicidata
    -0.46
     Tư
    -0.46
    POSITIVE LOGITS
    ginx
    0.85
     AssemblyTitle
    0.81
     nginx
    0.80
    WSGI
    0.72
    nginx
    0.70
     server
    0.66
     hosting
    0.64
    frastructure
    0.63
     Hosting
    0.63
    thâu
    0.63
    Activations Density 0.172%

    No Known Activations