© 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. 17-GEMMASCOPE-RES-16K
    6. 8592
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons or contrasts in data-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.85
    .');
    -0.73
    .[/
    -0.69
    .");
    -0.66
    Izvori
    -0.66
    .";
    -0.66
    ."));
    -0.65
    SceneManagement
    -0.63
    .}}
    -0.62
    Referencer
    -0.62
    POSITIVE LOGITS
     include
    0.68
     externi
    0.67
    :
    0.58
     заключается
    0.58
     includes
    0.56
    :
    
    0.56
     şun
    0.53
    的是
    0.53
     folgendes
    0.53
     عبارت
    0.52
    Activations Density 0.492%

    No Known Activations