© 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. 8517
    Prev
    Next
    INDEX
    Explanations

    references to the concept of weakness or weak conditions in various 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
    fromLTRB
    -0.57
    邃
    -0.57
     تضيفلها
    -0.56
    AndEndTag
    -0.54
     iParam
    -0.54
     onBind
    -0.53
    mrow
    -0.53
     allen
    -0.53
    ถึง
    -0.51
     samme
    -0.51
    POSITIVE LOGITS
     weak
    1.83
     Weak
    1.66
    Weak
    1.53
    weak
    1.52
     weakly
    1.39
     weaker
    1.35
     weakest
    1.30
    WEAK
    1.21
     débil
    1.19
     mild
    1.18
    Activations Density 0.054%

    No Known Activations