© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9972
    Prev
    Next
    INDEX
    Explanations

    error handling and configuration issues within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /**
    -0.52
    
    -0.51
     مواليد
    -0.51
    /*
    -0.51
    出版年
    -0.50
    "]);
    
    -0.48
     صوتيه
    -0.48
    "){
    
    -0.47
    '));
    
    -0.46
    WebElementEntity
    -0.46
    POSITIVE LOGITS
     Python
    0.63
     python
    0.60
     Py
    0.59
     py
    0.56
    Python
    0.54
    python
    0.52
    py
    0.52
     None
    0.51
     PY
    0.47
    Py
    0.46
    Activations Density 1.397%

    No Known Activations