© 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. 7-GEMMASCOPE-RES-16K
    11. 4956
    Prev
    Next
    INDEX
    Explanations

    names of corporations and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.97
    OGND
    -0.84
     للاسماء
    -0.79
    sedown
    -0.79
     NDEBUG
    -0.77
     gynhyrchwyd
    -0.75
    uxxxx
    -0.75
     fashiola
    -0.73
     كومونز
    -0.73
    Personensuche
    -0.72
    POSITIVE LOGITS
    ,
    0.60
     (
    0.59
      
    0.51
    則是
    0.47
     are
    0.44
    ;
    0.44
     and
    0.41
    .
    0.39
     also
    0.39
    といった
    0.39
    Activations Density 1.115%

    No Known Activations