© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 725
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to JSON and its serialization

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

    terms related to JSON data processing and serialization

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

    json parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PLWABN
    -0.69
    protoimpl
    -0.61
    рации
    -0.61
    DebuggerNonUser
    -0.59
    ValueStyle
    -0.58
    ła
    -0.55
    Билгалдахарш
    -0.55
     ocasión
    -0.55
    RegressionTest
    -0.54
    Autoritní
    -0.54
    POSITIVE LOGITS
     كومونز
    0.84
    %)$
    0.73
    processData
    0.72
    HasForeignKey
    0.72
    GeoNames
    0.71
    s
    0.71
    toJSON
    0.69
    PMC
    0.67
     оригіналу
    0.65
    sidemargin
    0.65
    Activations Density 0.035%

    No Known Activations