© 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. 6506
    Prev
    Next
    INDEX
    Explanations

    code-related commands and outputs

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

    Printing to console or standard error

    np_acts-logits-general · gemini-2.0-flash

    outputting console text

    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
     typelib
    -0.93
     EClass
    -0.86
     виправивши
    -0.79
    Personendaten
    -0.78
    CreateMap
    -0.78
    expandindo
    -0.78
    
    -0.77
     &___
    -0.77
     betweenstory
    -0.76
    TargetException
    -0.76
    POSITIVE LOGITS
    println
    0.76
     println
    0.60
     print
    0.59
    print
    0.54
     said
    0.53
    printf
    0.50
     printed
    0.48
     Print
    0.47
    prin
    0.47
     printf
    0.45
    Activations Density 0.019%

    No Known Activations