Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2488
    Prev
    Next
    INDEX
    Explanations

    references to parcels of land, including their acreage and ownership details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rosca
    -0.55
    mayr
    -0.49
     zařízení
    -0.46
    dymyr
    -0.45
    vska
    -0.43
     rather
    -0.43
    גרת
    -0.43
    Tube
    -0.43
    ganu
    -0.42
    προ
    -0.42
    POSITIVE LOGITS
     plots
    1.25
     Plots
    1.14
     acres
    1.07
     parcels
    1.04
     plot
    1.03
     lands
    1.02
    Plots
    0.98
     land
    0.97
     parcel
    0.97
     acreage
    0.97
    Activations Density 0.277%

    No Known Activations