© 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. 30-GEMMASCOPE-RES-16K
    11. 10842
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and functions, particularly those associated with JSON processing and API context

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

    Working with JSON objects

    np_acts-logits-general · gemini-2.0-flash

    json serialization and deserialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wpdb
    -0.38
    Coffee
    -0.37
    prepareStatement
    -0.36
     coffee
    -0.36
    Tor
    -0.35
     ujednoznacz
    -0.35
     Tor
    -0.35
     kasarigan
    -0.35
     AssemblyCulture
    -0.35
     Coffee
    -0.32
    POSITIVE LOGITS
     JSON
    1.36
     json
    1.27
    JSON
    1.20
    json
    1.16
    Json
    1.03
     JSONObject
    1.02
     Json
    1.00
     JSONArray
    0.92
    JSONObject
    0.92
    JSONArray
    0.86
    Activations Density 0.564%

    No Known Activations