© 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. 10-GEMMASCOPE-RES-16K
    6. 6465
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connective phrases in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.37
     Majefty
    -1.02
     myſelf
    -1.02
     Monfieur
    -0.95
     ―――――
    -0.94
     Theſe
    -0.92
    ſelf
    -0.92
     Reſ
    -0.90
     Eſ
    -0.87
     Jefus
    -0.87
    POSITIVE LOGITS
     although
    0.84
     hence
    0.77
     therefore
    0.77
     поэтому
    0.69
    hence
    0.68
     consequently
    0.67
     may
    0.66
     should
    0.65
     will
    0.64
     can
    0.64
    Activations Density 0.567%

    No Known Activations