© 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. 15-GEMMASCOPE-RES-16K
    6. 1728
    Prev
    Next
    INDEX
    Explanations

    references to parameters or annotations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.76
     queſta
    -0.75
     indígen
    -0.72
     '\\;'
    -0.69
     linkovi
    -0.67
    PreferredItem
    -0.66
    sizeCache
    -0.63
    tinyos
    -0.63
    AsUp
    -0.61
    uestamente
    -0.60
    POSITIVE LOGITS
     @
    0.81
     
    0.67
     \
    0.61
     $
    0.59
     $\
    0.57
    @
    0.56
     *@
    0.54
     #
    0.53
    #
    0.53
    *@
    0.51
    Activations Density 0.025%

    No Known Activations