© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 34-GEMMASCOPE-RES-16K
    11. 10839
    Prev
    Next
    INDEX
    Explanations

    references to figures or illustrations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reſ
    -0.54
     juſ
    -0.44
     Inſ
    -0.43
     ſon
    -0.41
     ſta
    -0.39
     Perſ
    -0.39
     ſtand
    -0.39
    HtmlAttribute
    -0.38
     Chriftian
    -0.38
     Diſ
    -0.37
    POSITIVE LOGITS
     Figure
    3.08
     figure
    2.92
    Figure
    2.81
     Fig
    2.56
    figure
    2.48
    Fig
    2.33
     fig
    2.23
     figura
    2.23
     FIGURE
    2.20
     Figures
    2.17
    Activations Density 1.971%

    No Known Activations