© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1319
    Prev
    Next
    INDEX
    Explanations

    references to or terms related to web server configuration and HTTP request handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, IPs, "client," and web requests

    np_acts-logits-general · gemini-2.0-flash

    IP addresses and client requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rodillas
    -0.44
    pflich
    -0.44
     war
    -0.43
    war
    -0.43
     anuales
    -0.42
     sposa
    -0.42
     obligatoire
    -0.41
     festas
    -0.41
     ruedas
    -0.40
    ーズ
    -0.40
    POSITIVE LOGITS
     IP
    1.30
     ip
    1.01
     IPs
    0.96
    IP
    0.96
    ipAddress
    0.87
    IPs
    0.87
    IpAddress
    0.86
     Ip
    0.86
    Ip
    0.84
    userAgent
    0.83
    Activations Density 0.234%

    No Known Activations