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 - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 3203
    Prev
    Next
    INDEX
    Explanations

    terms related to JSON and data serialization

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

    JSON and json-related terms

    np_acts-logits-general · gemini-2.0-flash

    json

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     assolutamente
    -0.69
    Tikang
    -0.68
     Tilly
    -0.63
    initis
    -0.63
     bandou
    -0.63
    oarece
    -0.61
    RegressionTest
    -0.60
    linearGradient
    -0.59
    bióticos
    -0.58
    =-=-=-=-
    -0.56
    POSITIVE LOGITS
     json
    1.29
    json
    1.22
     Json
    1.19
     JSON
    1.13
    Json
    1.07
    JSON
    0.95
    ToJson
    0.89
    fromJson
    0.87
    jsonwebtoken
    0.84
    fastjson
    0.83
    Activations Density 0.052%

    No Known Activations