© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 7517
    Prev
    Next
    INDEX
    Explanations

    notations or symbols related to statistical estimators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цездатний
    -0.81
     Teich
    -0.73
     gouvernements
    -0.69
     Majesté
    -0.68
    ьаж
    -0.67
     agences
    -0.66
     كمان
    -0.63
    illance
    -0.62
     Roskov
    -0.62
    fromnode
    -0.62
    POSITIVE LOGITS
     Indiana
    0.91
    Indiana
    0.79
     Hoo
    0.70
    hat
    0.68
    apiClient
    0.68
     INDIANA
    0.66
     Hat
    0.65
    NB
    0.63
     Harrison
    0.63
    ugier
    0.62
    Activations Density 0.061%

    No Known Activations