© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7842
    Prev
    Next
    INDEX
    Explanations

    instances of the word "supplied" and its variations related to provision or supply

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.61
    OrNil
    -0.47
    Unavailable
    -0.45
     Dob
    -0.44
    куп
    -0.43
    dead
    -0.43
    omst
    -0.42
     Cir
    -0.42
    择
    -0.41
    ört
    -0.41
    POSITIVE LOGITS
    SUP
    1.28
     SUP
    1.19
    supp
    1.19
     Supp
    1.17
     supp
    1.14
     supervisory
    1.14
     supervise
    1.13
     supervising
    1.11
     supervised
    1.02
     Supplied
    1.02
    Activations Density 0.109%

    No Known Activations