© 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. 17-GEMMASCOPE-RES-16K
    11. 10281
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and specific grammatical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.94
    NUMX
    -0.93
    Lähteet
    -0.86
     MainAxisSize
    -0.81
    )";
    -0.80
    KURZBESCHREIBUNG
    -0.78
    Билгалдахарш
    -0.77
    ſelf
    -0.77
     iſt
    -0.77
     uſ
    -0.76
    POSITIVE LOGITS
     (
    1.09
     and
    0.91
     but
    0.81
     that
    0.80
     whilst
    0.79
    (
    0.77
     I
    0.75
     Whilst
    0.74
      
    0.73
    Whilst
    0.69
    Activations Density 0.483%

    No Known Activations