© 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. 10-GEMMASCOPE-RES-16K
    6. 12857
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to images and graphical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fundament
    -0.28
     ogen
    -0.28
     fund
    -0.27
    typeorm
    -0.27
     event
    -0.27
     app
    -0.27
     doba
    -0.26
    vertx
    -0.25
    fund
    -0.25
    element
    -0.25
    POSITIVE LOGITS
     snippetHide
    0.96
     للمعارف
    0.87
     يتيمه
    0.80
     nonUne
    0.79
    GEBURTS
    0.74
     pictured
    0.67
    hoodie
    0.65
    #+#
    0.63
    httphttps
    0.61
    AndEndTag
    0.60
    Activations Density 1.334%

    No Known Activations