© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 3752
    Prev
    Next
    INDEX
    Explanations

    numeric values and identifiers in a data structure or configuration file

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "));
    
    -0.48
    '),
    
    -0.47
    ︎
    -0.47
    '):
    
    -0.47
    ()));
    
    -0.47
    "):
    
    -0.46
    ")){
    
    -0.46
    =,
    -0.46
     []),
    -0.45
    "))
    
    -0.45
    POSITIVE LOGITS
     @"/
    0.63
    rsiniz
    0.57
     <<
    0.55
     meille
    0.51
     intenção
    0.50
     prévoir
    0.50
     pulizia
    0.50
     złota
    0.50
     znamen
    0.49
     betekenis
    0.49
    Activations Density 1.574%

    No Known Activations