© 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. 18-GEMMASCOPE-RES-16K
    11. 15748
    Prev
    Next
    INDEX
    Explanations

    references to facilities and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "facility" or "facilities"

    np_acts-logits-general · gemini-2.0-flash

    facilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StatelessWidget
    -0.80
    resave
    -0.79
     يتيمه
    -0.79
     CreateTagHelper
    -0.79
    gemeester
    -0.75
    sidemargin
    -0.75
     مشين
    -0.74
    GraphicsUnit
    -0.73
    ftagPool
    -0.73
     allAfrica
    -0.73
    POSITIVE LOGITS
     facilities
    1.28
     facility
    1.07
     Facilities
    1.01
     FACILITIES
    1.01
    Facilities
    1.00
    facilities
    1.00
     Facility
    0.94
    facility
    0.93
     FACILITY
    0.90
    Facility
    0.89
    Activations Density 0.099%

    No Known Activations