© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7531
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and visual presentations related to stereoscopic images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fotos
    -0.40
     Fotos
    -0.35
    arthur
    -0.34
    Osob
    -0.32
    Arthur
    -0.32
     ficam
    -0.32
    Photos
    -0.31
    FOTOS
    -0.30
    nesc
    -0.29
     constitutional
    -0.29
    POSITIVE LOGITS
     image
    3.00
    image
    2.53
     Image
    2.30
    Image
    2.14
     IMAGE
    2.00
     imagem
    1.96
     imagen
    1.86
    IMAGE
    1.75
     immagine
    1.71
     images
    1.57
    Activations Density 0.244%

    No Known Activations