© 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. 6326
    Prev
    Next
    INDEX
    Explanations

    common contractions and possessive forms in language

    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
    AndEndTag
    -0.76
    Personendaten
    -0.71
    
    -0.64
    ześnie
    -0.62
    okovic
    -0.60
    ?";
    -0.57
    }';
    -0.57
    ajevo
    -0.57
     UNAM
    -0.56
    énario
    -0.55
    POSITIVE LOGITS
     theres
    0.79
     thats
    0.77
     shes
    0.76
     youre
    0.73
     whats
    0.72
     Thats
    0.71
     Theres
    0.70
     isnt
    0.70
    Twas
    0.70
     theyre
    0.69
    Activations Density 0.134%

    No Known Activations