© 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. 4785
    Prev
    Next
    INDEX
    Explanations

    phrases indicating struggles or challenges in understanding programming concepts and language structure

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

    JavaScript code snippets or explanations

    np_acts-logits-general · gemini-2.0-flash

    javascript code and concepts

    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
    شان
    -0.51
     them
    -0.42
     her
    -0.38
     Sem
    -0.38
     sem
    -0.38
     heb
    -0.38
    Enciclopedia
    -0.37
    หนึ่ง
    -0.36
     hand
    -0.35
     Pe
    -0.34
    POSITIVE LOGITS
    RectangleBorder
    0.89
     myſelf
    0.81
     насељу
    0.80
    EndInit
    0.79
     purpoſe
    0.79
     jsPsych
    0.76
    ArgsConstructor
    0.68
     whoſe
    0.68
     Monfieur
    0.67
    antaranya
    0.67
    Activations Density 0.026%

    No Known Activations