© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 10443
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly those used at the end of sentences or questions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Мексичка
    -0.41
    enedor
    -0.39
    ғ
    -0.37
    plasia
    -0.37
    moveToFirst
    -0.36
     flesta
    -0.35
    uerre
    -0.35
     թվական
    -0.34
    RESS
    -0.34
    ingway
    -0.34
    POSITIVE LOGITS
    -------
    0.66
    তথ্যসূত্র
    0.61
     يتيمه
    0.59
    SequentialGroup
    0.56
    verwijspagina
    0.54
    zelfde
    0.51
     nonUne
    0.49
    gether
    0.49
    󠁿
    0.48
    queous
    0.48
    Activations Density 0.826%

    No Known Activations