© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14919
    Prev
    Next
    INDEX
    Explanations

    legal terms and citations related to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    zzleHttp
    -0.48
    ActionCreators
    -0.46
    setupUi
    -0.46
    новниш
    -0.46
    eterangan
    -0.46
     habet
    -0.43
    NDR
    -0.42
    phylococcus
    -0.42
    datable
    -0.42
    "$_
    -0.41
    POSITIVE LOGITS
    prnewswire
    0.41
    3
    0.40
     Fleck
    0.39
     Мексичка
    0.39
    <?
    0.38
    Vía
    0.38
     Amb
    0.36
     跳转至
    0.36
    샵
    0.35
    BorderStyle
    0.35
    Activations Density 0.714%

    No Known Activations