© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2576
    Prev
    Next
    INDEX
    Explanations

    code segments related to programming structures and syntax, particularly loops and variable assignments

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

    Code snippets with indexing/looping

    np_acts-logits-general · gemini-2.0-flash

    nested loops with indices

    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
     صوتيه
    -0.95
     متعلقه
    -0.76
    fromnode
    -0.71
    BeginContext
    -0.69
    rawDesc
    -0.68
     OFDb
    -0.67
    RTDA
    -0.67
    GHIJKLM
    -0.63
    Begriffsklä
    -0.61
    তথ্যসূত্র
    -0.61
    POSITIVE LOGITS
    multer
    0.57
     []:
    0.54
     acompanhar
    0.49
    Personensuche
    0.48
     nachfol
    0.47
     accompanying
    0.47
     relever
    0.47
     zugleich
    0.45
    ustes
    0.44
     nearby
    0.44
    Activations Density 0.208%

    No Known Activations