© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 209
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tslib
    -0.49
    intios
    -0.47
    出版年
    -0.47
     Roskov
    -0.46
    interopRequire
    -0.45
     Acorn
    -0.45
     LL
    -0.44
     HL
    -0.44
    VZ
    -0.44
     Ried
    -0.43
    POSITIVE LOGITS
    luster
    0.77
    lustre
    0.68
    Lack
    0.67
     Lack
    0.65
     thereof
    0.63
     lack
    0.59
     luster
    0.51
     gebre
    0.49
     lustre
    0.44
    Falta
    0.43
    Activations Density 0.131%

    No Known Activations