© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7351
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" in various contexts, indicating a focus on deficiencies or absence of something

    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
    Portale
    -0.70
     Biggs
    -0.62
    XtraEditors
    -0.61
     nho
    -0.60
     heaviest
    -0.60
     parka
    -0.59
    EndContext
    -0.59
     Medellín
    -0.58
    erevan
    -0.57
     Urbano
    -0.57
    POSITIVE LOGITS
     lack
    3.61
     Lack
    3.29
    Lack
    3.26
    lack
    3.02
     lacks
    2.69
     lacked
    2.64
     lacking
    2.53
     manque
    1.99
    缺乏
    1.94
     falta
    1.80
    Activations Density 0.083%

    No Known Activations