© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2993
    Prev
    Next
    INDEX
    Explanations

    instances of exclamatory sentences or punctuation

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

    punctuation followed by conjunctions/pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     because
    -1.67
    because
    -1.51
    Because
    -1.41
     Because
    -1.39
     porque
    -1.31
     Çünkü
    -1.29
     karena
    -1.27
    因为
    -1.26
     Потому
    -1.25
     BECAUSE
    -1.22
    POSITIVE LOGITS
     Shouldn
    0.72
     Surely
    0.69
     surely
    0.65
    Surely
    0.64
    Shouldn
    0.63
     shouldn
    0.60
    hould
    0.57
    Зноскі
    0.57
     فريبيس
    0.57
     hObject
    0.53
    Activations Density 0.104%

    No Known Activations