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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 2600
    Prev
    Next
    INDEX
    Explanations

    specific programming and web service-related technical terms

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

    Code-related words and API names

    np_acts-logits-general · gemini-2.0-flash

    web service APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.38
     stores
    -0.38
     instruction
    -0.36
    úrese
    -0.35
    پور
    -0.35
     rays
    -0.33
     stroke
    -0.33
    дж
    -0.33
    #+#
    -0.32
     natura
    -0.32
    POSITIVE LOGITS
    wsdl
    0.69
    ServiceModel
    0.68
    ThroughAttribute
    0.67
     springfox
    0.65
     getService
    0.64
    JAXB
    0.63
     Remote
    0.63
     service
    0.63
     Service
    0.62
    WebService
    0.62
    Activations Density 0.433%

    No Known Activations