© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14329
    Prev
    Next
    INDEX
    Explanations

    content related to healthcare and medical research

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

    preceding "or"

    np_acts-logits-general · gemini-2.0-flash

    or

    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
     mxArray
    -0.88
    "]);
    
    -0.77
     autorytatywna
    -0.73
    CodedInputStream
    -0.70
    "])
    
    -0.69
    "]));
    -0.68
    ']):
    -0.68
    ")));
    
    -0.68
    PreferredItem
    -0.67
    ">:
    -0.67
    POSITIVE LOGITS
     or
    4.30
     или
    3.19
    或
    2.85
     atau
    2.81
     eller
    2.71
     hoặc
    2.65
    或者
    2.62
     یا
    2.59
     nebo
    2.54
     alebo
    2.53
    Activations Density 7.559%

    No Known Activations