© 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 EvalsExportsAPI 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. 5085
    Prev
    Next
    INDEX
    Explanations

    tokenized fragments and keywords related to programming logic and conditions

    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
     rağmen
    -0.67
     dolayı
    -0.63
     Zudem
    -0.60
     nedeniyle
    -0.59
     защото
    -0.59
     nedenle
    -0.59
     ktorí
    -0.58
    私には
    -0.57
     tačiau
    -0.55
     그는
    -0.55
    POSITIVE LOGITS
    bootstrapcdn
    0.80
     cæ
    0.77
    awtextra
    0.74
     eſſ
    0.72
    それ
    0.71
     $_(
    0.71
     हाल
    0.69
     ſch
    0.69
     semelh
    0.68
     למע
    0.66
    Activations Density 1.021%

    No Known Activations