© 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 EvalsExportsinterp-engineNEWAPI 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. 5040
    Prev
    Next
    INDEX
    Explanations

    the presence of the phrase "as is" in a variety of contexts

    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
     GenerationType
    -1.09
    tagext
    -0.91
     BoxDecoration
    -0.91
    ArrowToggle
    -0.83
    UnusedPrivate
    -0.82
     CreateTagHelper
    -0.82
    IsContent
    -0.80
    出版年
    -0.78
    StoryboardSegue
    -0.76
    expandindo
    -0.76
    POSITIVE LOGITS
     hom
    0.52
    ционно
    0.50
    namics
    0.50
     fall
    0.47
     itself
    0.46
     kini
    0.46
    MSI
    0.46
    iros
    0.44
    kalan
    0.44
    זי
    0.43
    Activations Density 0.219%

    No Known Activations