© 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. 11-GEMMASCOPE-RES-16K
    11. 10996
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months, particularly "December" and "September."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     сидит
    -0.34
     игрушки
    -0.34
    la
    -0.31
    big
    -0.31
    圳
    -0.30
    ic
    -0.30
     înal
    -0.30
    guruan
    -0.30
    stüt
    -0.29
    сыл
    -0.29
    POSITIVE LOGITS
     December
    1.45
     February
    1.45
     September
    1.45
     October
    1.39
    December
    1.38
     August
    1.38
     January
    1.38
    February
    1.36
    September
    1.36
     November
    1.34
    Activations Density 0.144%

    No Known Activations