© 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. 16-GEMMASCOPE-RES-16K
    11. 2062
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quality or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    describing qualities or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.92
     betweenstory
    -0.91
    ſelves
    -0.78
    URLException
    -0.75
    ſelf
    -0.71
    bability
    -0.69
     myſelf
    -0.68
     Jefus
    -0.67
     themſelves
    -0.66
    ,:);
    -0.65
    POSITIVE LOGITS
     for
    0.72
     in
    0.65
     to
    0.65
     as
    0.54
     at
    0.51
     enough
    0.50
    navigationItem
    0.48
     from
    0.48
    ArgumentParser
    0.47
     here
    0.46
    Activations Density 0.263%

    No Known Activations