© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8507
    Prev
    Next
    INDEX
    Explanations

    questions and statements about beliefs or opinions

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

    Question-like utterances or statements of disagreement

    np_acts-logits-general · gemini-2.0-flash

    question tags and confirmations

    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
     termica
    -0.52
     cucchia
    -0.49
     communiquez
    -0.46
     Dott
    -0.45
    .}\
    -0.44
     Siti
    -0.43
     Outback
    -0.43
    zcze
    -0.43
     ù
    -0.43
     contratto
    -0.43
    POSITIVE LOGITS
    ymce
    0.77
    grees
    0.69
     XCTest
    0.68
    ocry
    0.67
    phors
    0.65
    uchtet
    0.65
    estanden
    0.65
    $_['
    0.64
    graphique
    0.64
    ínű
    0.63
    Activations Density 0.052%

    No Known Activations