© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1302
    Prev
    Next
    INDEX
    Explanations

    references to affordability or low-cost items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.89
    enumi
    -0.88
    enderror
    -0.85
    RegistryLite
    -0.81
     يتيمه
    -0.79
     față
    -0.73
    UnsafeEnabled
    -0.73
    ISODE
    -0.73
     stroller
    -0.73
    aarrggbb
    -0.73
    POSITIVE LOGITS
     cheap
    2.97
    Cheap
    2.62
     Cheap
    2.58
    cheap
    2.55
     cheaper
    2.30
     cheaply
    2.20
     cheapest
    2.10
     inexpensive
    2.05
     billig
    1.85
     Cheaper
    1.80
    Activations Density 0.045%

    No Known Activations