© 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. 12-GEMMASCOPE-RES-16K
    11. 1866
    Prev
    Next
    INDEX
    Explanations

    specific references to drawings 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 @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikiseite
    -0.52
    </tfoot>
    -0.47
     wikipagina
    -0.46
     quedarse
    -0.43
    Referințe
    -0.42
     Pristupljeno
    -0.42
    Caracteristici
    -0.42
    NOPQRST
    -0.42
    ismet
    -0.42
    visející
    -0.42
    POSITIVE LOGITS
    Drawing
    3.42
     Drawing
    2.92
     drawing
    2.72
    drawing
    2.55
     DRAWING
    2.28
     Drawings
    1.83
     drawings
    1.81
     draw
    1.81
    Draw
    1.77
    DRAW
    1.70
    Activations Density 0.035%

    No Known Activations