© 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. 41-GEMMASCOPE-RES-16K
    6. 7320
    Prev
    Next
    INDEX
    Explanations

    references to trails and outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.54
     '\\;'
    -0.48
    kháu
    -0.47
    pushFollow
    -0.45
    UrlResolution
    -0.44
    jsxFileName
    -0.44
    PRNewswire
    -0.43
    ########.
    -0.43
     Kompon
    -0.42
    twimg
    -0.42
    POSITIVE LOGITS
     campground
    1.13
     campsites
    1.11
     camping
    1.05
     campsite
    1.01
     Campground
    1.00
     campers
    0.94
    Camping
    0.94
     Camping
    0.93
     camp
    0.93
    camping
    0.90
    Activations Density 0.252%

    No Known Activations