© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11248
    Prev
    Next
    INDEX
    Explanations

    references to JSON data and its associated operations

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

    Mentions "json" or "Json"

    np_acts-logits-general · gemini-2.0-flash

    json parsing and serialization

    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
    ///<
    -0.69
    Tikang
    -0.63
    linearGradient
    -0.60
     Tilly
    -0.57
    dersfield
    -0.57
    initis
    -0.56
     assolutamente
    -0.56
     NPA
    -0.56
    LayoutParams
    -0.55
    checkNotNull
    -0.55
    POSITIVE LOGITS
     незавершена
    0.91
     للمعارف
    0.90
     json
    0.81
     Json
    0.79
    jackson
    0.75
     astore
    0.73
    json
    0.72
    fromJson
    0.69
    HasForeignKey
    0.68
     StatefulWidget
    0.68
    Activations Density 0.053%

    No Known Activations