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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15467
    Prev
    Next
    INDEX
    Explanations

    instances of potential legal implications or violations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.78
     ProtoMessage
    -0.69
    🥲
    -0.61
    ']")
    -0.61
    AddTagHelper
    -0.59
     arm
    -0.58
     otomatig
    -0.58
    }{*}{}
    -0.57
    DeleteBehavior
    -0.57
    ///</
    -0.56
    POSITIVE LOGITS
     USART
    0.57
    xtext
    0.48
     chief
    0.47
    Tembelea
    0.46
     pinulongan
    0.46
     sabbia
    0.45
    crumb
    0.45
    DJANGO
    0.44
    luß
    0.43
    Haupt
    0.43
    Activations Density 0.471%

    No Known Activations