© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 2008
    Prev
    Next
    INDEX
    Explanations

    references to academic or technical elements, particularly related to documents and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    嘧
    -0.63
    oredCriteria
    -0.56
     außer
    -0.54
    DataView
    -0.53
    ielded
    -0.48
    Попис
    -0.47
    RegressionTest
    -0.46
    actionMode
    -0.46
    Trama
    -0.45
    sweise
    -0.45
    POSITIVE LOGITS
    abestanden
    0.77
    VersionUID
    0.72
    Personensuche
    0.70
     ostavi
    0.70
    arXiv
    0.68
     Efq
    0.68
     fhort
    0.67
    bibitem
    0.67
     BnF
    0.67
     purpoſe
    0.66
    Activations Density 2.354%

    No Known Activations