© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4936
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conclusions or observations in research

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

    Preceding words of the word "that"

    np_acts-logits-general · gemini-2.0-flash

    conclusion that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quels
    -0.72
    PYX
    -0.54
    iverr
    -0.49
    ::*;
    -0.48
    quien
    -0.47
    Demografía
    -0.46
     relâche
    -0.44
    퀴
    -0.44
    Pautan
    -0.43
     quien
    -0.43
    POSITIVE LOGITS
     that
    3.61
     bahwa
    2.13
    that
    2.11
     rằng
    1.89
     dass
    1.68
     bahawa
    1.67
     ότι
    1.64
     że
    1.63
     kwamba
    1.57
     että
    1.54
    Activations Density 2.139%

    No Known Activations