© 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 - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 2143
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data, particularly focusing on parsing and handling JSON or similar data types

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

    structured data in programming or markup languages, particularly focusing on related content and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    קישורים
    -0.54
     uska
    -0.53
    ::{
    -0.49
    verbs
    -0.49
    HasAnnotation
    -0.48
     hell
    -0.48
     Hell
    -0.47
    ENDIAN
    -0.47
     MainAxisSize
    -0.47
    =[];
    -0.46
    POSITIVE LOGITS
    الإنجليزية
    0.93
    RegressionTest
    0.73
     purpoſe
    0.70
     Monfieur
    0.69
    expandindo
    0.67
     quæ
    0.66
    WriteTagHelper
    0.64
     chofe
    0.64
     reaſon
    0.63
     poffe
    0.61
    Activations Density 0.485%

    No Known Activations