© 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. 4759
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to software programming and system vulnerabilities

    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
    فایل‌لار
    -0.68
     wake
    -0.53
    ngdoc
    -0.50
     sex
    -0.49
     waking
    -0.49
    vous
    -0.49
    那是
    -0.47
     taste
    -0.47
     wakes
    -0.47
    titleMargin
    -0.47
    POSITIVE LOGITS
     CREEK
    0.56
    niająca
    0.55
     Embassy
    0.55
     foster
    0.54
    HasAnnotation
    0.54
    FundMe
    0.54
     FOSTER
    0.52
    OCCURRED
    0.51
     IMPLIED
    0.51
    {}'.
    0.51
    Activations Density 2.572%

    No Known Activations