© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    references to intelligence committees and related investigations

    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
    httphttps
    -0.78
    ########.
    -0.75
    thâu
    -0.70
    RenderAtEndOf
    -0.70
    AddTagHelper
    -0.67
    ſchaft
    -0.65
    ſſung
    -0.63
     myſelf
    -0.63
    parsedMessage
    -0.62
     AssemblyCulture
    -0.62
    POSITIVE LOGITS
     gustaría
    0.39
     sucede
    0.37
    mathrm
    0.34
    把
    0.31
     suced
    0.31
    ’
    0.28
    ブ
    0.28
     anledning
    0.28
    toare
    0.28
     kemungkinan
    0.28
    Activations Density 2.985%

    No Known Activations