© 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. 2-GEMMASCOPE-RES-16K
    11. 274
    Prev
    Next
    INDEX
    Explanations

    the word "the" and its variations to identify references to specific subjects or objects

    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
    inflater
    -0.53
    ]-->
    -0.52
     inilah
    -0.50
     graisse
    -0.48
     voulons
    -0.44
    iotti
    -0.44
    '];?>
    -0.44
    agos
    -0.44
    
    -0.43
    推荐阅读
    -0.43
    POSITIVE LOGITS
     on
    1.31
    onthe
    1.05
    OnThe
    0.96
     On
    0.95
    On
    0.93
    RegressionTest
    0.90
     на
    0.86
     ON
    0.85
    OnTop
    0.83
     onError
    0.82
    Activations Density 0.225%

    No Known Activations